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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -gay
    -0.08
    �
    -0.06
    _CH
    -0.06
     loaf
    -0.06
    pects
    -0.06
    세
    -0.06
     Daughter
    -0.06
    าะ
    -0.06
    qu
    -0.06
    cljs
    -0.06
    POSITIVE LOGITS
    ออกแบบ
    0.06
     optimizing
    0.06
     LIB
    0.06
    ektor
    0.06
     gén
    0.06
    .map
    0.06
    agner
    0.06
     fasta
    0.06
     여러분
    0.06
     optimization
    0.06
    Act Density 0.002%

    No Known Activations