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

    Neuronpedia

    INDEX
    Explanations

    if

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lavoro
    -0.07
    _Offset
    -0.07
     redesigned
    -0.06
     astronomers
    -0.06
     announc
    -0.06
    _position
    -0.06
     bombings
    -0.06
    "math
    -0.06
     levy
    -0.06
    .FileInputStream
    -0.06
    POSITIVE LOGITS
    ús
    0.08
    .console
    0.07
    Want
    0.07
    ü
    0.06
    喔
    0.06
    isti
    0.06
     via
    0.06
    ób
    0.06
    (if
    0.06
    �
    0.06
    Act Density 0.036%

    No Known Activations