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

    Neuronpedia

    INDEX
    Explanations

    say "capitalized names"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    '''↵↵
    -0.07
     elek
    -0.07
    vre
    -0.07
    Scene
    -0.07
     इसस
    -0.06
    LEGAL
    -0.06
    enum
    -0.06
     complic
    -0.06
    .
↵
↵
    -0.06
    Document
    -0.06
    POSITIVE LOGITS
    availability
    0.07
     (^
    0.07
     џ
    0.06
    (eventName
    0.06
     친구
    0.06
    /fl
    0.06
    .sessions
    0.06
    Tên
    0.06
    acey
    0.06
     aliases
    0.06
    Act Density 0.011%

    No Known Activations