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

    Neuronpedia

    INDEX
    Explanations

    rain doing thing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     While
    0.81
    Если
    0.80
    While
    0.80
    ˃
    0.78
     Whilst
    0.76
     During
    0.75
    Important
    0.75
     important
    0.75
     Every
    0.74
     Important
    0.73
    POSITIVE LOGITS
    volent
    0.81
    нтов
    0.78
    ocalypse
    0.72
    savefig
    0.70
    crazy
    0.70
    giant
    0.69
    djangoproject
    0.69
    }):
    0.68
    codegen
    0.67
    autiful
    0.67
    Act Density 0.000%

    No Known Activations