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

    Neuronpedia

    INDEX
    Explanations

    abbreviations and punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arriving
    -0.07
    _compat
    -0.07
    ření
    -0.07
    dba
    -0.06
    .est
    -0.06
    _beta
    -0.06
    -u
    -0.06
    _group
    -0.06
    'es
    -0.06
    -server
    -0.06
    POSITIVE LOGITS
     outpatient
    0.07
    声音
    0.07
     Franti
    0.07
     lässt
    0.06
     розк
    0.06
    _gshared
    0.06
    Enemy
    0.06
     ghế
    0.06
    無し�
    0.06
    .PLAIN
    0.06
    Act Density 0.089%

    No Known Activations