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

    Neuronpedia

    INDEX
    Explanations

    commands followed by context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⸩
    0.60
     théorème
    0.54
     ignoreString
    0.52
    髹
    0.51
     england
    0.50
    ޘ
    0.49
    題目
    0.48
     purnama
    0.48
     امتحان
    0.48
     pcMove
    0.47
    POSITIVE LOGITS
    7
    0.59
    and
    0.58
    ,
    0.53
    -
    0.53
     chain
    0.52
    5
    0.50
    ad
    0.49
     and
    0.48
    chain
    0.46
     capabilities
    0.46
    Act Density 0.000%

    No Known Activations