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

    Neuronpedia

    INDEX
    Explanations

    names and aliases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obfusc
    0.20
     data
    0.19
     방법에
    0.19
     different
    0.19
     metadata
    0.19
     semantics
    0.19
     Änderung
    0.19
     granularity
    0.18
     decrement
    0.18
     user
    0.18
    POSITIVE LOGITS
    𓃵
    0.25
     aka
    0.25
     ওরফে
    0.24
     उर्फ
    0.24
    ၊
    0.21
     AKA
    0.21
     (†
    0.20
    ගේ
    0.20
     quien
    0.20
    ؒ
    0.19
    Act Density 2.359%

    No Known Activations