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

    Neuronpedia

    INDEX
    Explanations

    dialogue

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _imm
    -0.07
    outlined
    -0.06
     tud
    -0.06
     nous
    -0.06
     arrows
    -0.06
    )‏
    -0.06
     ioutil
    -0.06
    _handles
    -0.06
     relaxing
    -0.06
    -media
    -0.06
    POSITIVE LOGITS
     выб
    0.07
     пес
    0.07
     Ware
    0.07
     SOC
    0.07
    ولی
    0.07
     Sistem
    0.07
    ίναι
    0.07
    ToolTip
    0.06
    addafi
    0.06
    -small
    0.06
    Act Density 0.033%

    No Known Activations