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

    Neuronpedia

    INDEX
    Explanations

    technical or scientific contexts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     conditioner
    -0.08
    爽
    -0.07
    िड
    -0.07
     thresholds
    -0.07
    vd
    -0.07
    StateManager
    -0.07
     Ấ
    -0.06
    .Range
    -0.06
     right
    -0.06
     çöz
    -0.06
    POSITIVE LOGITS
    mtime
    0.06
    .addr
    0.06
    008
    0.06
     veins
    0.06
    _seg
    0.05
     haystack
    0.05
    _reverse
    0.05
     نزدیک
    0.05
     paed
    0.05
     mainBundle
    0.05
    Act Density 0.175%

    No Known Activations