Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases related to cooking methods and ingredient handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Location or part of an object

    np_acts-logits-general · gemini-2.0-flash

    edges of objects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     judiciales
    -0.66
     policiales
    -0.60
     fiscales
    -0.57
     ampliamente
    -0.55
     regeringen
    -0.54
     econó
    -0.54
    bbene
    -0.54
     fiables
    -0.54
     sanitarias
    -0.53
     automatiques
    -0.52
    POSITIVE LOGITS
     edges
    1.07
     sides
    1.05
     ends
    0.95
     underside
    0.93
     insides
    0.90
     tops
    0.88
     corners
    0.84
     outer
    0.81
     outside
    0.81
     inside
    0.80
    Act Density 0.576%

    No Known Activations