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

    Neuronpedia

    INDEX
    Explanations

    his

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (super
    -0.07
    MOOTH
    -0.07
     sar
    -0.06
    ь
    -0.06
    익
    -0.06
    مي
    -0.06
     brushed
    -0.06
     सत
    -0.06
    三
    -0.06
    이라고
    -0.06
    POSITIVE LOGITS
    desc
    0.07
     haben
    0.07
     inc
    0.07
    ication
    0.07
    ☴
    0.06
     Started
    0.06
    escription
    0.06
    LOCK
    0.06
    -cap
    0.06
    ICON
    0.06
    Act Density 0.580%

    No Known Activations