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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cow
    -0.07
    Prov
    -0.06
     flee
    -0.06
     cof
    -0.06
    @api
    -0.06
    _building
    -0.06
    ottes
    -0.06
    IDES
    -0.06
    .basic
    -0.06
    anten
    -0.06
    POSITIVE LOGITS
    bufio
    0.07
    adult
    0.06
    ～～
    0.06
    lasyon
    0.06
    	go
    0.06
     diye
    0.06
    .getTag
    0.06
    :↵
    0.06
     asla
    0.06
     Fragen
    0.06
    Act Density 0.004%

    No Known Activations