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

    Neuronpedia

    INDEX
    Explanations

    wagon

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Multimedia
    -0.07
     心
    -0.06
     zwe
    -0.06
     scant
    -0.06
    ,np
    -0.06
    τικές
    -0.06
    $class
    -0.06
     ValueError
    -0.06
    _interfaces
    -0.06
     disrupt
    -0.06
    POSITIVE LOGITS
    ◆
    0.07
    追
    0.06
     technolog
    0.06
     legally
    0.06
     pom
    0.06
     bản
    0.06
    .resp
    0.06
    neg
    0.06
    ।
    0.06
     ##↵
    0.06
    Act Density 0.002%

    No Known Activations