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

    Neuronpedia

    INDEX
    Explanations

    nuclear

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stuck
    -0.07
    .**************↵
    -0.07
    (".");↵
    -0.07
     dictionary
    -0.06
     CHRIST
    -0.06
    tein
    -0.06
    ственных
    -0.06
     sớm
    -0.06
    ello
    -0.06
     Lith
    -0.06
    POSITIVE LOGITS
    .[
    0.06
     WITHOUT
    0.06
     conservatives
    0.06
    getUser
    0.06
     flirting
    0.06
     자
    0.06
    sono
    0.06
     Suffolk
    0.06
     Couples
    0.06
     Health
    0.06
    Act Density 0.003%

    No Known Activations