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

    Neuronpedia

    INDEX
    Explanations

    courtroom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    lad
    -0.07
    rays
    -0.07
    梁
    -0.07
     досвід
    -0.06
    erts
    -0.06
    iniz
    -0.06
    Addresses
    -0.06
    edList
    -0.06
    asures
    -0.06
    thrown
    -0.06
    POSITIVE LOGITS
     lifted
    0.07
    '
↵
    0.07
     socio
    0.07
     joe
    0.07
     Wichita
    0.07
     sorts
    0.07
     happening
    0.06
     슈
    0.06
     attribution
    0.06
    _tip
    0.06
    Act Density 0.008%

    No Known Activations