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

    Neuronpedia

    INDEX
    Explanations

    soft

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    挓
    -0.08
    �
    -0.07
     EITHER
    -0.07
    مخاطر
    -0.07
    圪
    -0.07
    emade
    -0.07
    乩
    -0.07
     rentals
    -0.07
    _news
    -0.06
    ibraltar
    -0.06
    POSITIVE LOGITS
    щик
    0.08
    权威
    0.07
     great
    0.07
    BE
    0.07
     awards
    0.06
    .Interface
    0.06
     respect
    0.06
    0.06
     monarch
    0.06
    ']]
    0.06
    Act Density 0.000%

    No Known Activations