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

    Neuronpedia

    INDEX
    Explanations

    subjective statements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ciudad
    -0.07
    fuse
    -0.06
     پیشنهاد
    -0.06
    (mappedBy
    -0.06
    URLConnection
    -0.06
    ergus
    -0.06
    ेष
    -0.06
    lán
    -0.06
    _smart
    -0.06
    ン
    -0.06
    POSITIVE LOGITS
    раз
    0.08
    (sim
    0.07
    sciously
    0.07
     […]↵↵
    0.07
    LAB
    0.07
     korun
    0.07
     wrath
    0.06
    =:
    0.06
     einz
    0.06
    CFG
    0.06
    Act Density 0.082%

    No Known Activations