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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RESPONSE
    -0.07
    Detect
    -0.06
    ец
    -0.06
    Gamma
    -0.06
    (sequence
    -0.06
     graduating
    -0.06
    _value
    -0.06
    translation
    -0.06
     Denied
    -0.06
     Sandbox
    -0.06
    POSITIVE LOGITS
     Young
    0.06
     sinus
    0.06
    čila
    0.06
     bis
    0.06
    ↵↵
    0.06
    ################################################################################
    0.06
     tyre
    0.06
     ост
    0.06
     Brand
    0.06
    !↵↵
    0.06
    Act Density 0.033%

    No Known Activations