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

    Neuronpedia

    INDEX
    Explanations

    View

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     slogan
    -0.08
     pn
    -0.08
     pl
    -0.07
     Verb
    -0.06
    OA
    -0.06
    Profile
    -0.06
     Bd
    -0.06
    Q
    -0.06
     SharedModule
    -0.06
    (+
    -0.06
    POSITIVE LOGITS
    illed
    0.06
    -condition
    0.06
    levant
    0.06
    `.
    0.06
    oop
    0.06
     frenzy
    0.06
    以下
    0.06
    また
    0.05
    :size
    0.05
    ails
    0.05
    Act Density 0.013%

    No Known Activations