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

    Neuronpedia

    INDEX
    Explanations

    retroviruses

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -step
    -0.07
     Kurds
    -0.07
    ada
    -0.06
    tery
    -0.06
     Signs
    -0.06
    path
    -0.06
     گن
    -0.06
    callback
    -0.06
    ۲
    -0.06
     بع
    -0.06
    POSITIVE LOGITS
    ();
↵
    0.07
     shiny
    0.06
    );

↵
    0.06
    .trailing
    0.06
    amphetamine
    0.06
     guten
    0.06
     považ
    0.06
     °
    0.06
     Scarborough
    0.06
     kms
    0.06
    Act Density 0.008%

    No Known Activations