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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    *pi
    -0.07
    LETTE
    -0.07
    ,D
    -0.06
    =d
    -0.06
    اگ
    -0.06
    Like
    -0.06
    HttpRequest
    -0.06
    _EV
    -0.06
     spont
    -0.06
    ⟩
    -0.06
    POSITIVE LOGITS
    생
    0.07
     blacklist
    0.07
    _superuser
    0.07
     Normally
    0.07
     label
    0.06
    rdf
    0.06
    ующ
    0.06
     Dummy
    0.06
     indebted
    0.06
    -Length
    0.06
    Act Density 0.020%

    No Known Activations