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

    Neuronpedia

    INDEX
    Explanations

    procedural descriptions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bret
    -0.07
     bespoke
    -0.07
     FTP
    -0.07
     unlike
    -0.07
    NSNotificationCenter
    -0.07
     лид
    -0.07
    "I
    -0.06
    antically
    -0.06
     decks
    -0.06
    𝐭
    -0.06
    POSITIVE LOGITS
    warning
    0.08
    💇
    0.07
    translation
    0.07
     kvinne
    0.07
     للغا
    0.07
     emoji
    0.07
    �
    0.07
    jamin
    0.06
    _choice
    0.06
    urd
    0.06
    Act Density 0.052%

    No Known Activations