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

    Neuronpedia

    INDEX
    Explanations

    division into groups/stages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     нада
    -0.07
     midfield
    -0.06
    しい
    -0.06
    GLuint
    -0.06
     multicast
    -0.06
     FileName
    -0.06
    ;,
    -0.05
    Colon
    -0.05
     исч
    -0.05
    ;"><
    -0.05
    POSITIVE LOGITS
    andle
    0.07
    daf
    0.06
    rych
    0.06
    'l
    0.06
    -and
    0.06
    ق
    0.06
    _TYP
    0.06
    チュ
    0.06
    κο
    0.06
    rink
    0.06
    Act Density 0.319%

    No Known Activations