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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :
↵
↵
    -0.07
    Digest
    -0.06
     konum
    -0.06
    _THE
    -0.06
     aviation
    -0.06
     Při
    -0.06
    .create
    -0.06
    ").↵↵
    -0.06
    ункт
    -0.06
     emulation
    -0.06
    POSITIVE LOGITS
    Slf
    0.07
     spor
    0.06
    _tp
    0.06
     knocked
    0.06
    -headed
    0.06
    รร
    0.06
     cart
    0.06
     pours
    0.06
    ’ll
    0.06
     knowledge
    0.06
    Act Density 0.042%

    No Known Activations