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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (bar
    -0.07
     manpower
    -0.07
    uese
    -0.06
     tady
    -0.06
     notre
    -0.06
     списка
    -0.06
    �
    -0.06
     USHORT
    -0.06
    Her
    -0.06
    pdo
    -0.06
    POSITIVE LOGITS
     transitional
    0.06
     affected
    0.06
     predators
    0.06
    choose
    0.06
     Fires
    0.06
     trustees
    0.06
     Vill
    0.06
     composite
    0.06
     Malaysia
    0.06
     soared
    0.06
    Act Density 0.000%

    No Known Activations