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

    Neuronpedia

    INDEX
    Explanations

    allow

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wong
    -0.07
    Ryan
    -0.06
     Dut
    -0.06
    돌
    -0.06
     Tinder
    -0.06
    ію
    -0.06
    経
    -0.06
     Gur
    -0.05
     '".
    -0.05
    이에
    -0.05
    POSITIVE LOGITS
    _TEXT
    0.08
    olist
    0.07
     Fucked
    0.06
    ateway
    0.06
    -tool
    0.06
    -chain
    0.06
     telemetry
    0.06
    .sigma
    0.06
     Repos
    0.06
     orders
    0.06
    Act Density 0.186%

    No Known Activations