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

    Neuronpedia

    INDEX
    Explanations

    nv

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     readability
    -0.07
     yp
    -0.07
     physic
    -0.07
    Tab
    -0.07
    أك
    -0.06
     Stereo
    -0.06
     Freeman
    -0.06
    gorithm
    -0.06
    _subtype
    -0.06
    .Method
    -0.06
    POSITIVE LOGITS
     NV
    0.11
    NV
    0.07
    ov
    0.07
     constructors
    0.07
    v
    0.06
     Howell
    0.06
    _NV
    0.06
     名前
    0.06
    aving
    0.06
     is
    0.06
    Act Density 0.001%

    No Known Activations