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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *v
    -0.07
    	rs
    -0.07
     macOS
    -0.07
     РФ
    -0.07
    *f
    -0.06
     tylko
    -0.06
     gs
    -0.06
    _ios
    -0.06
     сез
    -0.06
    makt
    -0.06
    POSITIVE LOGITS
    _session
    0.07
    -thread
    0.06
     interpolated
    0.06
    лова
    0.06
     نگهد
    0.06
     devel
    0.06
    _REASON
    0.06
    !↵↵↵↵
    0.06
    Reject
    0.06
    Invalid
    0.06
    Act Density 0.006%

    No Known Activations