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

    Neuronpedia

    INDEX
    Explanations

    Code/Documentation Snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ็
    -0.07
    vají
    -0.06
     Seriously
    -0.06
    Actually
    -0.06
    UBE
    -0.06
    ثال
    -0.06
     göre
    -0.06
    CheckBox
    -0.06
    ーパ
    -0.06
     domin
    -0.06
    POSITIVE LOGITS
    八
    0.06
    鼓
    0.06
    	property
    0.06
    owners
    0.06
     miscar
    0.06
     ∧
    0.06
     cx
    0.06
    	Page
    0.06
     fals
    0.06
    ”.↵↵
    0.06
    Act Density 0.003%

    No Known Activations