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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     관
    -0.07
     Gore
    -0.07
    」を
    -0.07
    �
    -0.07
    _MC
    -0.07
     planetary
    -0.06
     э
    -0.06
     Terr
    -0.06
    opers
    -0.06
     Lana
    -0.06
    POSITIVE LOGITS
     TSR
    0.07
    unction
    0.07
    古屋
    0.07
     scissors
    0.06
    ToOne
    0.06
     upstream
    0.06
    pNext
    0.06
    _cache
    0.06
    有限公司
    0.06
    :'',↵
    0.06
    Act Density 0.005%

    No Known Activations