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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ...'↵
    -0.06
    İs
    -0.06
     gris
    -0.06
     hộp
    -0.06
    ahtar
    -0.06
     Tro
    -0.06
    аних
    -0.06
     جدید
    -0.06
     bộ
    -0.06
    )s
    -0.06
    POSITIVE LOGITS
     fracking
    0.08
     awaits
    0.07
     Activate
    0.07
    -calendar
    0.07
     computers
    0.07
    selling
    0.07
    .Commands
    0.06
     "!
    0.06
    /manage
    0.06
    Force
    0.06
    Act Density 0.001%

    No Known Activations