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

    Neuronpedia

    INDEX
    Explanations

    mathematical closed interval problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _failure
    -0.08
    _t
    -0.08
    _black
    -0.08
    embers
    -0.08
     tobacco
    -0.08
    _fake
    -0.08
    _tw
    -0.08
     Mehrheit
    -0.08
     negro
    -0.08
    દર
    -0.08
    POSITIVE LOGITS
    限定
    0.10
     NOTICE
    0.08
     সীম
    0.08
     boundaries
    0.08
     sın
    0.08
    有限
    0.08
    <Menu
    0.08
     सीम
    0.08
     "-
    0.08
    限制
    0.07
    Act Density 0.024%

    No Known Activations