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

    Neuronpedia

    INDEX
    Explanations

    /

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    变得
    -0.07
    티
    -0.06
    _BS
    -0.06
    kę
    -0.06
     disdain
    -0.06
    ARGS
    -0.06
    ktop
    -0.06
    VALUE
    -0.06
    classpath
    -0.06
    _scal
    -0.06
    POSITIVE LOGITS
    opro
    0.07
    (Board
    0.06
     Telegraph
    0.06
    ubber
    0.06
     properly
    0.06
    -signed
    0.06
     unstoppable
    0.06
     nedenle
    0.06
    hoa
    0.06
    ором
    0.06
    Act Density 0.005%

    No Known Activations