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

    Neuronpedia

    INDEX
    Explanations

    programming and data structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vorg
    0.48
     Thief
    0.48
     Stir
    0.47
    לב
    0.46
     Chosen
    0.45
     Tasting
    0.44
    颂
    0.44
    年纪
    0.44
     Avenger
    0.44
     Bane
    0.44
    POSITIVE LOGITS
    ess
    0.50
    aks
    0.50
    anches
    0.50
    anj
    0.50
    eras
    0.50
    ense
    0.49
    ga
    0.48
    alo
    0.48
    ine
    0.48
    ide
    0.47
    Act Density 0.001%

    No Known Activations