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

    Neuronpedia

    INDEX
    Explanations

    Exercise warm-up/cool-down

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    stration
    -0.08
     deprived
    -0.07
    owych
    -0.07
     AIS
    -0.07
     odbor
    -0.07
    seller
    -0.07
    ifica
    -0.06
    ippines
    -0.06
    Hundreds
    -0.06
     vlády
    -0.06
    POSITIVE LOGITS
    أك
    0.07
     edeb
    0.06
    _FRONT
    0.06
    _att
    0.06
     ','.
    0.06
    ;,
    0.06
     undead
    0.06
    .StartsWith
    0.06
     offset
    0.06
    Feb
    0.05
    Act Density 0.015%

    No Known Activations