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

    Neuronpedia

    INDEX
    Explanations

    code with labels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    etimes
    -0.07
     ook
    -0.07
    زين
    -0.07
     Mob
    -0.07
    �
    -0.07
    rawidłow
    -0.07
    ố
    -0.07
    ▰
    -0.07
     holds
    -0.07
    SIM
    -0.07
    POSITIVE LOGITS
    ונג
    0.07
    _columns
    0.07
    .zoom
    0.07
    oba
    0.07
    _start
    0.07
    参照
    0.07
     Param
    0.06
     источ
    0.06
     Colon
    0.06
     Composite
    0.06
    Act Density 0.039%

    No Known Activations