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

    Neuronpedia

    INDEX
    Explanations

    loop index assignment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    okovic
    0.73
    raining
    0.71
    壢
    0.70
     গঙ্গ
    0.69
     colleges
    0.66
    asures
    0.65
    జు
    0.64
    রাসের
    0.63
    izações
    0.63
    eningen
    0.63
    POSITIVE LOGITS
    Ampl
    0.84
    ImagePath
    0.82
     Def
    0.82
    Absolute
    0.81
     Topic
    0.81
    Topic
    0.79
    റൽ
    0.78
     healthiest
    0.77
    Def
    0.76
     Api
    0.76
    Act Density 0.004%

    No Known Activations