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

    Neuronpedia

    INDEX
    Explanations

    without

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .workspace
    -0.07
    杷
    -0.07
    ๏
    -0.07
    actly
    -0.07
     Capital
    -0.07
     Fu
    -0.06
    .Location
    -0.06
    powiedź
    -0.06
     oppressive
    -0.06
    挑衅
    -0.06
    POSITIVE LOGITS
    HTTPRequest
    0.07
     ALLOW
    0.07
    slide
    0.07
    answers
    0.07
    _callbacks
    0.07
    heartbeat
    0.07
    tree
    0.06
    EB
    0.06
    Vals
    0.06
    auth
    0.06
    Act Density 0.003%

    No Known Activations