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

    Neuronpedia

    INDEX
    Explanations

    percentage

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     أمر
    -0.06
     Pharmacy
    -0.06
    脸
    -0.06
     приблиз
    -0.06
    292
    -0.06
     écrit
    -0.06
    /*================================================================
    -0.06
    )=>{↵
    -0.05
     Minerals
    -0.05
    ))));↵
    -0.05
    POSITIVE LOGITS
    IDDEN
    0.08
    clock
    0.07
    ingly
    0.07
     tph
    0.07
     annoying
    0.07
    arah
    0.07
    esimal
    0.06
    σου
    0.06
     onslaught
    0.06
     armored
    0.06
    Act Density 0.104%

    No Known Activations