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

    Neuronpedia

    INDEX
    Explanations

    Code or configuration files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     студент
    -0.07
     ty
    -0.07
     Tod
    -0.07
    涮
    -0.07
     currencies
    -0.06
     amused
    -0.06
    OX
    -0.06
    stin
    -0.06
     Zukunft
    -0.06
     temples
    -0.06
    POSITIVE LOGITS
     parental
    0.07
    -validate
    0.07
    ernel
    0.06
     Images
    0.06
    -frame
    0.06
    陕西省
    0.06
    .defaultProps
    0.06
    -file
    0.06
    _steps
    0.06
    Storm
    0.06
    Act Density 0.028%

    No Known Activations