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

    Neuronpedia

    INDEX
    Explanations

    Password security

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     prow
    -0.06
     teachers
    -0.06
     mascot
    -0.06
     EVENT
    -0.06
    370
    -0.06
     BU
    -0.06
     Hey
    -0.06
     Unfortunately
    -0.06
     Himself
    -0.06
    unities
    -0.06
    POSITIVE LOGITS
     história
    0.07
     choisir
    0.06
    Text
    0.06
     jeux
    0.06
    .confirm
    0.06
    χές
    0.06
    ontvangst
    0.06
     Hebrew
    0.06
     agricult
    0.06
    romě
    0.06
    Act Density 0.143%

    No Known Activations