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

    Neuronpedia

    INDEX
    Explanations

    diagnosis

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     backlash
    -0.06
     Hy
    -0.06
    &T
    -0.06
     воды
    -0.06
    _effects
    -0.06
     обеспе
    -0.06
    IPC
    -0.06
     Warren
    -0.06
    _sha
    -0.06
    ROP
    -0.06
    POSITIVE LOGITS
     cancers
    0.07
    밍
    0.06
    (predictions
    0.06
    ){
↵
↵
    0.06
     Thank
    0.06
    .surname
    0.06
    _bool
    0.06
    ,status
    0.06
     stabil
    0.06
     having
    0.06
    Act Density 0.014%

    No Known Activations