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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    али
    -0.07
    erie
    -0.07
    ules
    -0.07
     flank
    -0.07
    ormap
    -0.07
    ude
    -0.07
    erne
    -0.07
     wicked
    -0.07
     Oro
    -0.07
     Drink
    -0.07
    POSITIVE LOGITS
     �
    0.08
    $this
    0.07
    っぽ
    0.07
     zien
    0.07
    Stripe
    0.07
     그냥
    0.07
     Созд
    0.06
     speaks
    0.06
     בש
    0.06
     zz
    0.06
    Act Density 0.099%

    No Known Activations