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

    Neuronpedia

    INDEX
    Explanations

    actions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ystems
    -0.08
    ioni
    -0.07
     Blind
    -0.07
     protections
    -0.07
    _ts
    -0.06
     comments
    -0.06
    ümüzde
    -0.06
     backbone
    -0.06
     Studios
    -0.06
    sport
    -0.06
    POSITIVE LOGITS
     deja
    0.07
    erap
    0.06
     ander
    0.06
    tok
    0.06
    Mov
    0.06
     IEnumerable
    0.06
    ="__
    0.06
    ellidos
    0.06
    $MESS
    0.06
    Intersection
    0.06
    Act Density 0.125%

    No Known Activations