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

    Neuronpedia

    INDEX
    Explanations

    switch statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rele
    -0.07
    ZF
    -0.07
    ido
    -0.06
    font
    -0.06
    edo
    -0.06
    $http
    -0.06
     Zion
    -0.06
    Trash
    -0.06
    lak
    -0.06
    SEQ
    -0.06
    POSITIVE LOGITS
     incentive
    0.07
     spokesman
    0.07
     ubytování
    0.06
     Thông
    0.06
     رئيس
    0.06
    shield
    0.06
     architectures
    0.06
     malé
    0.06
    iginal
    0.06
    .lista
    0.06
    Act Density 0.010%

    No Known Activations