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

    Neuronpedia

    INDEX
    Explanations

    code annotations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    temperatur
    0.38
    NIH
    0.37
    CrL
    0.37
    arrière
    0.35
    geschwindigkeit
    0.35
    Doming
    0.35
     ferrug
    0.35
    righteous
    0.35
     cirrh
    0.34
    cdZ
    0.34
    POSITIVE LOGITS
    注解
    0.53
     annotation
    0.46
     annotations
    0.44
     nullable
    0.43
     injectable
    0.41
    ="
    0.40
     /**@
    0.39
     })
    0.38
     注
    0.38
     prefixed
    0.38
    Act Density 0.034%

    No Known Activations