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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Tracks
    -0.07
     Santo
    -0.07
     مناسب
    -0.07
     criminals
    -0.07
     aproxim
    -0.07
    CreateTime
    -0.07
     disgust
    -0.06
     продаж
    -0.06
     Laravel
    -0.06
     mounted
    -0.06
    POSITIVE LOGITS
    pearance
    0.07
    ương
    0.07
    ServletRequest
    0.06
    teen
    0.06
    рав
    0.06
    tensor
    0.06
    保证
    0.06
    alance
    0.06
    iq
    0.06
    ortic
    0.06
    Act Density 0.020%

    No Known Activations