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

    Neuronpedia

    INDEX
    Explanations

    shelf and its surroundings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    iotics
    0.72
     indul
    0.71
    ixir
    0.69
    ượu
    0.68
     Ks
    0.66
    ʡ
    0.66
     KS
    0.64
    ievement
    0.64
    rophys
    0.63
    orium
    0.63
    POSITIVE LOGITS
     pung
    0.72
     Acho
    0.72
     light
    0.72
    Light
    0.71
     произво
    0.68
    light
    0.68
     weinig
    0.68
     madera
    0.67
     winged
    0.67
    豆
    0.67
    Act Density 0.001%

    No Known Activations