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

    Neuronpedia

    INDEX
    Explanations

    when

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     개최
    -0.07
    oping
    -0.07
    ोन
    -0.07
     mannen
    -0.06
     laundering
    -0.06
     Challenges
    -0.06
    Paper
    -0.06
     Berm
    -0.06
    Pers
    -0.06
    asures
    -0.06
    POSITIVE LOGITS
     kız
    0.06
    ={}
    0.06
     setPosition
    0.06
    _ATTRIB
    0.06
    =logging
    0.06
    (beta
    0.06
     stainless
    0.06
    (hit
    0.06
    _MON
    0.06
    개를
    0.06
    Act Density 0.072%

    No Known Activations