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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itting
    -0.08
     Dich
    -0.07
    =}
    -0.07
    _pw
    -0.07
     applaud
    -0.07
    Xem
    -0.06
    ini
    -0.06
     Nacional
    -0.06
    dto
    -0.06
    _login
    -0.06
    POSITIVE LOGITS
     Herc
    0.07
    मक
    0.07
     getP
    0.06
    EDIATE
    0.06
     �
    0.06
    aint
    0.06
     생
    0.06
     judgment
    0.06
    _PROVID
    0.06
    _Word
    0.06
    Act Density 0.003%

    No Known Activations