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

    Neuronpedia

    INDEX
    Explanations

    conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ="__
    -0.07
     опис
    -0.06
    Advance
    -0.06
    講
    -0.06
     만나
    -0.06
    _CLIP
    -0.06
     locationManager
    -0.06
    tracks
    -0.06
     minutos
    -0.06
     τις
    -0.06
    POSITIVE LOGITS
     STUD
    0.07
     distribution
    0.07
    _region
    0.07
     Distribution
    0.07
     arch
    0.07
     applaud
    0.07
     convened
    0.07
     listening
    0.06
    ={↵
    0.06
    lw
    0.06
    Act Density 0.017%

    No Known Activations