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

    Neuronpedia

    INDEX
    Explanations

    code/web content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    其他
    -0.07
     omega
    -0.07
     Psi
    -0.07
    scrollTop
    -0.07
     orb
    -0.06
     üç
    -0.06
     outfile
    -0.06
     Halloween
    -0.06
     posto
    -0.06
     состояния
    -0.06
    POSITIVE LOGITS
    VERSION
    0.06
    Ha
    0.06
    "--
    0.06
    .simps
    0.05
    ERING
    0.05
    .promise
    0.05
     biri
    0.05
    -shirt
    0.05
     ACTION
    0.05
    .crm
    0.05
    Act Density 0.086%

    No Known Activations