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

    Neuronpedia

    INDEX
    Explanations

    safety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -water
    -0.07
    э
    -0.07
     Sears
    -0.07
    rades
    -0.07
    anter
    -0.06
     mất
    -0.06
    importDefault
    -0.06
    idal
    -0.06
    animals
    -0.06
    л
    -0.06
    POSITIVE LOGITS
    “This
    0.06
     emot
    0.06
    “The
    0.06
     samot
    0.06
     CommonModule
    0.06
     GRAT
    0.06
    “She
    0.06
     palm
    0.06
    (ALOAD
    0.06
    _enter
    0.06
    Act Density 0.059%

    No Known Activations