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

    Neuronpedia

    INDEX
    Explanations

    technical descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Obj
    -0.07
     minors
    -0.07
     tools
    -0.06
    -symbol
    -0.06
     let
    -0.06
     tương
    -0.06
     tool
    -0.06
    oltage
    -0.06
    공
    -0.06
    ategy
    -0.06
    POSITIVE LOGITS
    	Read
    0.06
    öh
    0.06
    develop
    0.06
     achieving
    0.06
     Hil
    0.06
     coh
    0.06
     spl
    0.06
    ového
    0.06
    owi
    0.06
    RELATED
    0.06
    Act Density 0.204%

    No Known Activations