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

    Neuronpedia

    INDEX
    Explanations

    list items, separators, and continuations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     motivos
    0.57
     problemas
    0.51
     cobre
    0.51
     construido
    0.51
     grafo
    0.50
     matematica
    0.50
     llevo
    0.50
     variáveis
    0.49
     precisamente
    0.49
     exatamente
    0.48
    POSITIVE LOGITS
     alternative
    0.40
    tica
    0.40
    ut
    0.39
    t
    0.39
    Gym
    0.39
    putable
    0.39
    Baby
    0.38
    ous
    0.38
     alternatives
    0.38
    astrophe
    0.38
    Act Density 0.001%

    No Known Activations