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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADIO
    -0.07
    fw
    -0.07
     días
    -0.06
    @c
    -0.06
    nb
    -0.06
     parce
    -0.06
    わ
    -0.06
     сказала
    -0.06
    Eliminar
    -0.06
     अल
    -0.06
    POSITIVE LOGITS
    range
    0.07
    高中
    0.06
     qt
    0.06
    -from
    0.06
     modelling
    0.06
    liğin
    0.06
    ORDER
    0.06
     لر
    0.06
     regularization
    0.06
     wood
    0.06
    Act Density 0.000%

    No Known Activations