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

    Neuronpedia

    INDEX
    Explanations

    with a description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     consecuencias
    0.50
     жизнь
    0.50
     jederzeit
    0.46
     последствия
    0.43
     historias
    0.42
     eficacia
    0.42
     consequências
    0.41
     höchste
    0.41
     fatalities
    0.41
     misery
    0.40
    POSITIVE LOGITS
    itt
    0.39
    hunt
    0.38
    設け
    0.38
    ersk
    0.37
    yaw
    0.37
    /
    0.36
    signal
    0.36
    ett
    0.36
     Signal
    0.36
    Hunt
    0.36
    Act Density 0.000%

    No Known Activations