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
    相关
    -0.07
    ampil
    -0.07
     Analyzer
    -0.06
     Lego
    -0.06
     missionary
    -0.06
     років
    -0.06
     nightly
    -0.06
    —in
    -0.06
    -insert
    -0.06
    reta
    -0.06
    POSITIVE LOGITS
     μη
    0.07
    (productId
    0.07
     confess
    0.07
     phys
    0.06
    .any
    0.06
     แต
    0.06
    ICLE
    0.06
     Dup
    0.06
     Beh
    0.06
     Irr
    0.06
    Act Density 0.109%

    No Known Activations