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

    Neuronpedia

    INDEX
    Explanations

    colon

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     اللازمة
    -0.07
     масло
    -0.07
     PLUS
    -0.07
    _inline
    -0.06
     zwykł
    -0.06
     hyper
    -0.06
    하겠다
    -0.06
    השקעה
    -0.06
    кра
    -0.06
    חמישי
    -0.06
    POSITIVE LOGITS
     TOR
    0.08
     sail
    0.08
    ESS
    0.08
    év
    0.08
    清理
    0.07
    ѝ
    0.07
    aal
    0.07
    '-
    0.07
    	ADD
    0.07
    址
    0.07
    Act Density 0.053%

    No Known Activations