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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    749
    -0.07
    -svg
    -0.07
    —and
    -0.07
     doubts
    -0.06
    .jasper
    -0.06
    although
    -0.06
    僕
    -0.06
     آذ
    -0.06
    398
    -0.06
    Attempt
    -0.06
    POSITIVE LOGITS
     \"$
    0.06
    _listen
    0.06
     ticaret
    0.06
    hya
    0.06
     vatandaş
    0.06
     Obtain
    0.06
    远
    0.06
    };
↵
↵
    0.06
     VAN
    0.05
    strukce
    0.05
    Act Density 0.043%

    No Known Activations