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

    Neuronpedia

    INDEX
    Explanations

    Learning and development

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    UCCEEDED
    -0.06
    iná
    -0.06
    ٌ
    -0.06
    etest
    -0.06
     DEA
    -0.06
    _none
    -0.06
    ildo
    -0.06
    事
    -0.06
    iones
    -0.06
     oraz
    -0.06
    POSITIVE LOGITS
     spel
    0.07
    sofar
    0.06
    creens
    0.06
     Gret
    0.06
     Profession
    0.06
    곤
    0.06
    ky
    0.06
     airlines
    0.06
     LANG
    0.06
     Plaintiff
    0.06
    Act Density 0.052%

    No Known Activations