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

    Neuronpedia

    INDEX
    Explanations

    Version

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    نسا
    -0.07
    -sama
    -0.07
    ��
    -0.07
    一定
    -0.07
    ladım
    -0.07
    орош
    -0.07
    .Validation
    -0.07
    oks
    -0.06
     tzv
    -0.06
     assertTrue
    -0.06
    POSITIVE LOGITS
     Version
    0.07
     Glen
    0.07
     γλώ
    0.06
    فس
    0.06
    Characters
    0.06
    (V
    0.06
    =ax
    0.06
    Ay
    0.06
     coconut
    0.06
    Dr
    0.06
    Act Density 0.001%

    No Known Activations