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

    Neuronpedia

    INDEX
    Explanations

    replace

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Loving
    -0.08
     pillar
    -0.07
    Sphere
    -0.06
    cdot
    -0.06
     곧
    -0.06
    龙
    -0.06
    arin
    -0.06
     bondage
    -0.06
    irteen
    -0.06
     گردید
    -0.06
    POSITIVE LOGITS
    /hr
    0.06
    	eval
    0.06
     výraz
    0.06
    #include
    0.06
    _Normal
    0.06
     sca
    0.06
    luğ
    0.05
     çal
    0.05
     жов
    0.05
     simulator
    0.05
    Act Density 0.006%

    No Known Activations