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

    Neuronpedia

    INDEX
    Explanations

    citations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ｯ
    -0.06
    	flags
    -0.06
    _TIME
    -0.06
    FindBy
    -0.06
     Wak
    -0.06
     باد
    -0.06
    _INST
    -0.06
    缩
    -0.06
     그의
    -0.05
    仰
    -0.05
    POSITIVE LOGITS
     vaccine
    0.07
     caste
    0.07
    Tr
    0.06
    $file
    0.06
    gan
    0.06
    voke
    0.06
    ect
    0.06
    imenti
    0.06
    	api
    0.06
    orm
    0.06
    Act Density 0.014%

    No Known Activations