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

    Neuronpedia

    INDEX
    Explanations

    website data

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     genç
    -0.06
    Comic
    -0.06
     Tf
    -0.06
    lli
    -0.05
    ociety
    -0.05
    -kind
    -0.05
     الأرض
    -0.05
    curacy
    -0.05
    arlar
    -0.05
    凉
    -0.05
    POSITIVE LOGITS
     implies
    0.07
    !\
    0.07
    .setOnItemClickListener
    0.07
     který
    0.07
    !!!!!!!!
    0.07
     muj
    0.07
     medicinal
    0.07
     *}↵↵
    0.07
     Says
    0.07
    .we
    0.06
    Act Density 0.032%

    No Known Activations