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

    Neuronpedia

    INDEX
    Explanations

    deep-throat, inner voice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Agricult
    0.12
     Hid
    0.11
    ﹔
    0.10
     oftent
    0.10
    alaikums
    0.10
     //<
    0.10
     '',
    0.10
     inland
    0.10
     فونب
    0.10
     Physic
    0.10
    POSITIVE LOGITS
    IN
    0.14
    J
    0.12
    W
    0.12
    Break
    0.12
    Cage
    0.12
    X
    0.12
    St
    0.12
    S
    0.11
     snippet
    0.11
     snippets
    0.11
    Act Density 0.000%

    No Known Activations