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

    Neuronpedia

    INDEX
    Explanations

    Manner adverbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sai
    -0.07
    .detect
    -0.07
     답
    -0.06
    _parms
    -0.06
    AG
    -0.06
    enderror
    -0.06
     вариант
    -0.06
    érieur
    -0.06
    .steps
    -0.06
     Shed
    -0.06
    POSITIVE LOGITS
    MM
    0.07
     firewall
    0.07
     orchestra
    0.06
     foreground
    0.06
    _TRACE
    0.06
     nurse
    0.06
     callee
    0.06
    ully
    0.06
    监听
    0.06
    activ
    0.06
    Act Density 0.177%

    No Known Activations