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

    Neuronpedia

    INDEX
    Explanations

    hover

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aku
    -0.08
    Symbol
    -0.07
    .drawLine
    -0.07
    available
    -0.07
     Bylo
    -0.07
    odelist
    -0.06
    	password
    -0.06
    Baseline
    -0.06
    �
    -0.06
    flake
    -0.06
    POSITIVE LOGITS
    hover
    0.09
    hiro
    0.07
    説
    0.07
    _hover
    0.07
     hover
    0.07
     Fortunately
    0.06
     hobbies
    0.06
    커
    0.06
     Usually
    0.06
     heb
    0.06
    Act Density 0.003%

    No Known Activations