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

    Neuronpedia

    INDEX
    Explanations

    const

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bride
    -0.07
     Treasury
    -0.06
    SW
    -0.06
     narrator
    -0.06
    -data
    -0.06
     forgive
    -0.06
     Це
    -0.06
     MW
    -0.06
    _man
    -0.06
     сервер
    -0.06
    POSITIVE LOGITS
     itk
    0.08
    letal
    0.07
    ั้
    0.07
    씀
    0.07
    ]])↵
    0.06
    ,min
    0.06
     nabízí
    0.06
    .linkLabel
    0.06
     inflammatory
    0.06
    .jwt
    0.06
    Act Density 0.009%

    No Known Activations