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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     칼
    -0.07
     obsessed
    -0.07
     ost
    -0.06
    _chi
    -0.06
     Gods
    -0.06
     beneficiation
    -0.06
     ch
    -0.06
    ;n
    -0.06
    almart
    -0.06
    Elem
    -0.06
    POSITIVE LOGITS
     dereg
    0.07
    _gc
    0.06
    ��
    0.06
    ูร
    0.06
     DUP
    0.06
     cafeteria
    0.06
    .ToList
    0.06
    633
    0.06
     torture
    0.06
    .Big
    0.06
    Act Density 0.000%

    No Known Activations