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

    Neuronpedia

    INDEX
    Explanations

    degrees

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tenants
    -0.07
    _ring
    -0.07
    .modules
    -0.07
    .between
    -0.06
     vests
    -0.06
    ‐'
    -0.06
    .stage
    -0.06
     Persistence
    -0.06
     计
    -0.06
    Estado
    -0.06
    POSITIVE LOGITS
    hey
    0.08
    cstring
    0.07
    THIS
    0.07
    HEY
    0.06
    ENUM
    0.06
    nů
    0.06
    っ�
    0.06
     objectAtIndex
    0.06
    (jLabel
    0.06
     outspoken
    0.06
    Act Density 0.004%

    No Known Activations