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

    Neuronpedia

    INDEX
    Explanations

    back to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    集中
    -0.11
     concentrated
    -0.09
     Concentr
    -0.08
    (global
    -0.08
     concentrate
    -0.08
     Cran
    -0.08
     globale
    -0.07
     feitos
    -0.07
     concentration
    -0.07
     necessárias
    -0.07
    POSITIVE LOGITS
     espalda
    0.10
     hacia
    0.09
     تجاه
    0.08
     envers
    0.08
    -transparent
    0.08
     पीछे
    0.08
     belakang
    0.08
    aho
    0.08
     headed
    0.08
     offs
    0.08
    Act Density 0.005%

    No Known Activations