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

    Neuronpedia

    INDEX
    Explanations

    outside

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sher
    -0.06
    er
    -0.06
    _dialog
    -0.06
    otent
    -0.06
     Unicorn
    -0.06
     deterior
    -0.06
    Q
    -0.06
    uples
    -0.06
     celebr
    -0.06
    uzzer
    -0.05
    POSITIVE LOGITS
    如下
    0.08
    VICE
    0.07
    .Down
    0.07
     考
    0.07
    idge
    0.07
    Jacob
    0.07
     इ
    0.07
    outside
    0.07
    .visitMethodInsn
    0.07
     Jake
    0.07
    Act Density 0.007%

    No Known Activations