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

    Neuronpedia

    INDEX
    Explanations

    voluntary actions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Canon
    -0.07
     отсутств
    -0.06
    .legend
    -0.06
     Labor
    -0.06
     veterinarian
    -0.06
    _EDIT
    -0.06
     INS
    -0.06
     Ruby
    -0.06
    )을
    -0.06
    Stick
    -0.06
    POSITIVE LOGITS
    ira
    0.07
    76
    0.07
    225
    0.06
    imitive
    0.06
    (nb
    0.06
    χν
    0.06
    .maximum
    0.06
     lẫn
    0.06
    天堂
    0.06
    �
    0.06
    Act Density 0.115%

    No Known Activations