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

    Neuronpedia

    INDEX
    Explanations

    following him

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    avenir
    0.40
    mj
    0.39
    ীন্দ্র
    0.37
    ziele
    0.37
    మాల
    0.36
    astava
    0.36
    achen
    0.36
     chim
    0.36
    &=\
    0.36
     chip
    0.35
    POSITIVE LOGITS
    ResourceId
    0.44
    ContextHeader
    0.43
     playerScore
    0.42
    𝙼
    0.40
    ágico
    0.40
    クション
    0.39
    FieldNumber
    0.39
     danced
    0.38
     শোষণ
    0.37
     abused
    0.37
    Act Density 0.000%

    No Known Activations