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

    Neuronpedia

    INDEX
    Explanations

    roles and fungi description

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Keefe
    0.42
     আহবান
    0.42
     চেয়ারম্যান
    0.39
    治安
    0.39
    ೮
    0.39
    filesystem
    0.38
    电气
    0.38
    шим
    0.38
    倞
    0.38
    椛
    0.38
    POSITIVE LOGITS
     vet
    0.41
     patr
    0.40
    Princ
    0.38
     UG
    0.37
    PreferredItem
    0.37
     bal
    0.37
     prose
    0.35
     pat
    0.35
    Longrightarrow
    0.35
     high
    0.35
    Act Density 0.001%

    No Known Activations