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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cas
    -0.06
     Ago
    -0.06
    _SEP
    -0.06
     оз
    -0.06
     advancing
    -0.06
    Xã
    -0.05
     Pod
    -0.05
    Ос
    -0.05
     soak
    -0.05
    疆
    -0.05
    POSITIVE LOGITS
     homeowner
    0.08
    -module
    0.07
     hãng
    0.07
    _minimum
    0.07
     via
    0.07
     goodbye
    0.06
     permanent
    0.06
    173
    0.06
     undefined
    0.06
    flat
    0.06
    Act Density 0.000%

    No Known Activations