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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ifes
    -0.07
     чим
    -0.07
     جون
    -0.06
    �
    -0.06
    ول
    -0.06
     Jeb
    -0.06
    Mas
    -0.06
    olation
    -0.06
     iddia
    -0.06
    refix
    -0.06
    POSITIVE LOGITS
    Components
    0.07
     convened
    0.06
    posite
    0.06
    ργ
    0.06
    breadcrumb
    0.06
    (Page
    0.06
     resultCode
    0.06
     collusion
    0.06
    came
    0.06
     NAV
    0.05
    Act Density 0.000%

    No Known Activations