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

    Neuronpedia

    INDEX
    Explanations

    ass

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    服
    -0.07
     pave
    -0.07
     Phần
    -0.06
    отя
    -0.06
    _'.$
    -0.06
    ็
    -0.06
     confidentiality
    -0.06
    ectomy
    -0.06
    стин
    -0.06
    點
    -0.06
    POSITIVE LOGITS
     Prophet
    0.07
     Morales
    0.07
     filtering
    0.07
    .addField
    0.06
     Grinder
    0.06
     tim
    0.06
    .lv
    0.06
     OBJ
    0.06
     flavours
    0.06
    τικ
    0.06
    Act Density 0.081%

    No Known Activations