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

    Neuronpedia

    INDEX
    Explanations

    41

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Healing
    -0.07
    lobals
    -0.06
     roots
    -0.06
     iw
    -0.06
    �
    -0.06
     Corner
    -0.06
    古屋
    -0.06
    -Д
    -0.06
    Ba
    -0.06
    entin
    -0.06
    POSITIVE LOGITS
    REAL
    0.06
    QE
    0.06
    _rules
    0.06
    utations
    0.06
    702
    0.06
    _GRE
    0.06
     Siemens
    0.06
     Disconnect
    0.06
    ORIGINAL
    0.06
     نیم
    0.06
    Act Density 0.146%

    No Known Activations