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

    Neuronpedia

    INDEX
    Explanations

    sharing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (enum
    -0.07
     Meg
    -0.06
     společnost
    -0.06
     extras
    -0.06
     xt
    -0.06
     blending
    -0.06
     їм
    -0.06
     dy
    -0.06
                             ↵
    -0.06
     Lt
    -0.06
    POSITIVE LOGITS
    ZX
    0.07
    zion
    0.06
     Sanchez
    0.06
    ｯ
    0.06
     Essen
    0.06
     apprec
    0.06
    ears
    0.06
    egrated
    0.06
    �
    0.06
    _SUB
    0.06
    Act Density 0.033%

    No Known Activations