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

    Neuronpedia

    INDEX
    Explanations

    Portuguese technical content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    backward
    -0.07
    licos
    -0.06
    IRROR
    -0.06
    srv
    -0.06
     دختر
    -0.06
    剧
    -0.06
    喜
    -0.06
     reproductive
    -0.06
     Religion
    -0.06
     habitat
    -0.06
    POSITIVE LOGITS
     SSR
    0.07
    CLASS
    0.07
    Submitting
    0.06
    ــــــــ
    0.06
     �
    0.06
     congr
    0.06
    Maint
    0.06
     Hell
    0.06
    ammers
    0.06
    TXT
    0.06
    Act Density 0.028%

    No Known Activations