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

    Neuronpedia

    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    价值
    -0.07
    Indiana
    -0.06
     singer
    -0.06
    Wild
    -0.06
     playoffs
    -0.06
    Reminder
    -0.06
     Andres
    -0.06
     Horizon
    -0.06
     Blonde
    -0.06
     Dr
    -0.06
    POSITIVE LOGITS
     א
    0.06
     xyz
    0.06
    /G
    0.06
    FormField
    0.06
     overlook
    0.06
     animated
    0.06
    ают
    0.06
    επ
    0.06
     telecommunications
    0.06
     gep
    0.06
    Act Density 0.000%

    No Known Activations