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

    Neuronpedia

    INDEX
    Explanations

    itself

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    flu
    -0.07
    ILTER
    -0.07
    NDER
    -0.06
     halk
    -0.06
    CADE
    -0.06
    agination
    -0.06
     겨
    -0.06
    Burn
    -0.06
    โค
    -0.06
     LAST
    -0.06
    POSITIVE LOGITS
    ندان
    0.07
     Rename
    0.06
     neglig
    0.06
     dolphin
    0.06
    илась
    0.06
    scripts
    0.06
     وفق
    0.06
    不同
    0.06
     Ins
    0.06
     Bölgesi
    0.06
    Act Density 0.000%

    No Known Activations