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

    Neuronpedia

    INDEX
    Explanations

    btn-primary, btn-secondary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Kn
    0.44
    CAN
    0.41
    Whitney
    0.40
    Florence
    0.40
    Sophia
    0.40
    Cand
    0.39
     Fernanda
    0.38
    Peng
    0.37
    Gab
    0.37
    Comb
    0.37
    POSITIVE LOGITS
    outline
    0.75
    primary
    0.70
     outline
    0.66
     Outline
    0.63
     outlined
    0.63
     primaire
    0.62
     primary
    0.61
    secondary
    0.59
     Primary
    0.57
     sm
    0.56
    Act Density 0.001%

    No Known Activations