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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     reflection
    -0.07
     ei
    -0.07
     Sof
    -0.07
    -generic
    -0.07
    -pop
    -0.07
     bru
    -0.06
    PB
    -0.06
    沟
    -0.06
    Mob
    -0.06
    restrict
    -0.06
    POSITIVE LOGITS
    .argv
    0.06
     rept
    0.06
    няется
    0.06
     servings
    0.06
    //!
    0.06
    cret
    0.06
     calm
    0.06
    orative
    0.06
     applicationWill
    0.06
     patiently
    0.06
    Act Density 0.026%

    No Known Activations