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

    Neuronpedia

    INDEX
    Explanations

    Code/special characters

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itor
    -0.07
    subtype
    -0.07
     recognition
    -0.07
    YRO
    -0.06
     remove
    -0.06
    -0.06
    KC
    -0.06
     interruption
    -0.06
    stp
    -0.06
    Bre
    -0.06
    POSITIVE LOGITS
     白
    0.07
     Nä
    0.06
    .goal
    0.06
     قص
    0.06
     �
    0.06
    _relation
    0.06
    odí
    0.06
    �
    0.06
    ât
    0.06
    WARN
    0.06
    Act Density 0.008%

    No Known Activations