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

    Neuronpedia

    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     intensely
    -0.07
     containers
    -0.06
     dawn
    -0.06
     brainstorm
    -0.06
    Async
    -0.06
    jte
    -0.05
     فى
    -0.05
    安装
    -0.05
     Throw
    -0.05
    WindowText
    -0.05
    POSITIVE LOGITS
    orr
    0.07
    OSP
    0.07
    rientation
    0.06
    ●●●●
    0.06
     )[
    0.06
     eig
    0.06
    овер
    0.06
    ●●
    0.06
     modelName
    0.06
    Asset
    0.06
    Act Density 0.026%

    No Known Activations