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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [index
    -0.07
     Spain
    -0.07
     وص
    -0.07
     upward
    -0.07
     shack
    -0.07
     цель
    -0.06
     wie
    -0.06
     Forward
    -0.06
     disrupted
    -0.06
     BREAK
    -0.06
    POSITIVE LOGITS
    quota
    0.07
    ؤال
    0.06
    StyleSheet
    0.06
     IRS
    0.06
    bet
    0.06
    alphabet
    0.06
    PBS
    0.06
    HOST
    0.06
    atr
    0.06
    onth
    0.06
    Act Density 0.007%

    No Known Activations