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

    Neuronpedia

    INDEX
    Explanations

    greased

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     HM
    -0.07
    истем
    -0.07
    .pc
    -0.06
     looping
    -0.06
     cartridge
    -0.06
    돌
    -0.06
    roups
    -0.06
     ferv
    -0.06
     shocking
    -0.06
     punk
    -0.06
    POSITIVE LOGITS
    Alle
    0.07
    ฎ
    0.06
    Opaque
    0.06
     nation
    0.06
    /plain
    0.06
    _OPCODE
    0.06
     ded
    0.06
    _HANDLER
    0.06
    (plane
    0.06
    .setCode
    0.06
    Act Density 0.014%

    No Known Activations