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

    Neuronpedia

    INDEX
    Explanations

    programming/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     فلس
    -0.07
     bigot
    -0.06
     Gale
    -0.06
    locked
    -0.06
     eş
    -0.06
    	git
    -0.06
    哭
    -0.06
     Grim
    -0.06
     uh
    -0.06
     harsh
    -0.06
    POSITIVE LOGITS
    ]='
    0.07
     سری
    0.06
    Exports
    0.06
    Rem
    0.06
    イク
    0.06
     europ
    0.06
    ju
    0.06
    /:
    0.06
     Rem
    0.06
     جزء
    0.06
    Act Density 0.000%

    No Known Activations