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

    Neuronpedia

    INDEX
    Explanations

    ES

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     lak
    -0.07
     Rack
    -0.07
    διο
    -0.06
    \Controller
    -0.06
    
    -0.06
     riders
    -0.06
    Aud
    -0.06
    _team
    -0.06
    Ｄ
    -0.06
    _outer
    -0.06
    POSITIVE LOGITS
     steadfast
    0.07
    .leading
    0.07
     bacter
    0.06
    using
    0.06
    pizza
    0.06
     We
    0.06
    :before
    0.06
     stereotypes
    0.06
     emojis
    0.06
    vide
    0.06
    Act Density 0.000%

    No Known Activations