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

    Neuronpedia

    INDEX
    Explanations

    Technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Initialization
    -0.07
    フ�
    -0.07
    (surface
    -0.07
    _proj
    -0.06
    IDTH
    -0.06
    .pathname
    -0.06
     bahwa
    -0.06
    xcd
    -0.06
    <std
    -0.06
     painstaking
    -0.06
    POSITIVE LOGITS
     ethic
    0.07
    房
    0.07
     توسعه
    0.07
    Originally
    0.06
     march
    0.06
    unsupported
    0.06
    erv
    0.06
     chia
    0.06
     colon
    0.06
     白
    0.06
    Act Density 0.000%

    No Known Activations