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

    Neuronpedia

    INDEX
    Explanations

    code, text segments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zí
    -0.07
    etadata
    -0.07
     Ocak
    -0.07
     Utah
    -0.06
     Mobility
    -0.06
    ’av
    -0.06
    CTRL
    -0.06
    чук
    -0.06
    .subplots
    -0.06
    /english
    -0.06
    POSITIVE LOGITS
     pitching
    0.07
     freak
    0.07
    位
    0.07
    complete
    0.06
     госп
    0.06
     nightmare
    0.06
    ��
    0.06
    �新
    0.06
    质量
    0.06
     个
    0.06
    Act Density 0.000%

    No Known Activations