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

    Neuronpedia

    INDEX
    Explanations

    mostly

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _ERROR
    -0.09
    _IMETHOD
    -0.08
    _OVERRIDE
    -0.08
    _REQUEST
    -0.08
    _IOCTL
    -0.07
     عاد
    -0.07
    _RESPONSE
    -0.07
    rus
    -0.07
     संख्या
    -0.07
    _LEVEL
    -0.07
    POSITIVE LOGITS
     mostly
    0.14
    mostly
    0.13
     mainly
    0.12
     principalement
    0.12
     largely
    0.12
     Mostly
    0.12
     hauptsächlich
    0.11
    主要
    0.11
     voornamelijk
    0.11
    各种
    0.10
    Act Density 0.096%

    No Known Activations