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

    Neuronpedia

    INDEX
    Explanations

    Technical or scientific writing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     verse
    -0.07
    орони
    -0.07
    睛
    -0.07
     unwrap
    -0.06
     сест
    -0.06
    属性
    -0.06
    apphire
    -0.06
    ुरस
    -0.06
    lý
    -0.06
    itemId
    -0.06
    POSITIVE LOGITS
    防
    0.06
    akukan
    0.06
    	sem
    0.06
     equival
    0.06
     RH
    0.06
    estring
    0.06
    ozilla
    0.06
    .main
    0.06
    시키
    0.06
    rung
    0.06
    Act Density 0.011%

    No Known Activations