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

    Neuronpedia

    INDEX
    Explanations

    b

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ('=
    -0.07
     hollow
    -0.07
    _sprite
    -0.06
    ندي
    -0.06
    keley
    -0.06
     tad
    -0.06
     Benson
    -0.06
    rů
    -0.06
    ~,
    -0.06
    :'
    -0.06
    POSITIVE LOGITS
    AuthToken
    0.07
    >>();↵
    0.07
    apeut
    0.07
     Github
    0.06
     PhoneNumber
    0.06
    @JsonProperty
    0.06
    endars
    0.06
    XPath
    0.06
    .FirstName
    0.06
     NVIC
    0.06
    Act Density 0.005%

    No Known Activations