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

    Neuronpedia

    INDEX
    Explanations

    Java code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    endo
    -0.06
    _comment
    -0.06
    Processor
    -0.06
     essentials
    -0.06
    ляли
    -0.06
    dT
    -0.05
    _clean
    -0.05
    MENU
    -0.05
     pork
    -0.05
     hosp
    -0.05
    POSITIVE LOGITS
     Garmin
    0.08
    <Vec
    0.08
    ηγ
    0.07
     จำนวน
    0.07
    VEC
    0.07
     vaz
    0.06
     гаран
    0.06
     Gujar
    0.06
    инг
    0.06
     sentient
    0.06
    Act Density 0.018%

    No Known Activations