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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Các
    -0.07
    Mensaje
    -0.07
    ")));↵↵
    -0.07
     },
↵
↵
    -0.06
    Parse
    -0.06
    '),'
    -0.06
    _rb
    -0.06
    (rate
    -0.06
    ότητας
    -0.06
    Los
    -0.06
    POSITIVE LOGITS
     cpt
    0.07
     хими
    0.06
     zn
    0.06
     endorsed
    0.06
     estaba
    0.06
     وقد
    0.06
     subsidized
    0.06
     спост
    0.06
     provincia
    0.06
     inevitable
    0.06
    Act Density 0.005%

    No Known Activations