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

    Neuronpedia

    INDEX
    Explanations

    website legal disclaimers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Financial
    -0.07
     тільки
    -0.06
     bana
    -0.06
     Changing
    -0.06
    (candidate
    -0.06
     Centers
    -0.06
     progen
    -0.06
    Miller
    -0.06
     Worker
    -0.06
    Max
    -0.06
    POSITIVE LOGITS
     recurring
    0.07
     Buddhist
    0.06
    .ds
    0.06
    ợ
    0.06
     bás
    0.06
     pall
    0.06
     ghetto
    0.06
    ografie
    0.06
     Vince
    0.06
     unheard
    0.06
    Act Density 0.013%

    No Known Activations