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

    Neuronpedia

    INDEX
    Explanations

    Code documentation and errors

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fl
    -0.08
    -Fi
    -0.07
    איר
    -0.07
    ML
    -0.07
    muş
    -0.07
    והר
    -0.06
    火
    -0.06
    ottom
    -0.06
     Fus
    -0.06
    groups
    -0.06
    POSITIVE LOGITS
     шаг
    0.07
    	    ↵
    0.07
    ⓙ
    0.07
     linger
    0.07
     lar
    0.07
     facilit
    0.07
    קיץ
    0.06
    �
    0.06
     fetal
    0.06
     creampie
    0.06
    Act Density 0.028%

    No Known Activations