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

    Neuronpedia

    INDEX
    Explanations

    .framework

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     defends
    -0.07
    (binary
    -0.07
     resolves
    -0.07
    戰
    -0.07
     Tight
    -0.07
    뤘
    -0.07
    )/
    -0.07
    :model
    -0.07
    ㈼
    -0.07
    ecute
    -0.07
    POSITIVE LOGITS
     fertilizer
    0.08
     loans
    0.07
     пока
    0.07
    identifier
    0.07
     debt
    0.07
    ilers
    0.07
     HinderedRotor
    0.07
     müşteri
    0.07
    쉔
    0.07
     rail
    0.07
    Act Density 0.001%

    No Known Activations