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

    Neuronpedia

    INDEX
    Explanations

    environment variables and data access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Push
    0.44
    嘁
    0.44
     appending
    0.43
    জিওথের
    0.43
    Together
    0.42
    সিন
    0.40
     push
    0.40
    pyridazine
    0.40
     addObject
    0.39
     pushed
    0.39
    POSITIVE LOGITS
    ['
    0.66
    ["
    0.65
    ['-
    0.55
     ['
    0.50
    ']['
    0.50
    ')['
    0.49
    setdefault
    0.47
    __["
    0.46
    [`
    0.45
     ["
    0.45
    Act Density 0.005%

    No Known Activations