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

    Neuronpedia

    INDEX
    Explanations

    postponed tasks

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _RX
    -0.07
     id
    -0.07
     ejaculation
    -0.07
    _STARTED
    -0.06
    CTOR
    -0.06
    requencies
    -0.06
     WideString
    -0.06
    ipelines
    -0.06
    봉
    -0.06
    .Container
    -0.06
    POSITIVE LOGITS
    镲
    0.08
    做出
    0.08
     infinitely
    0.07
    نت
    0.07
     eas
    0.06
    emption
    0.06
     bootstrap
    0.06
    放进
    0.06
     artwork
    0.06
     Ket
    0.06
    Act Density 0.211%

    No Known Activations