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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Kaplan
    -0.06
    CHO
    -0.06
    ########################################################
    -0.06
     Plans
    -0.06
    DCF
    -0.06
     Survival
    -0.06
    ريط
    -0.06
    (selector
    -0.06
    .date
    -0.06
    тами
    -0.06
    POSITIVE LOGITS
     üzerinde
    0.07
    Victoria
    0.07
     현대
    0.07
     Dubai
    0.06
    ]=$
    0.06
    女
    0.06
     vel
    0.06
    adolu
    0.06
    egie
    0.06
    ━━━━━━━━
    0.06
    Act Density 0.000%

    No Known Activations