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

    Neuronpedia

    INDEX
    Explanations

    stopping spread of fire/infection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蓝
    -0.07
     een
    -0.07
     Shade
    -0.07
     Αρχ
    -0.06
    _off
    -0.06
    .crypto
    -0.06
    后
    -0.06
    اطعة
    -0.06
    inue
    -0.06
     end
    -0.06
    POSITIVE LOGITS
     phenomen
    0.07
    英
    0.06
     Wants
    0.06
    λαν
    0.06
    ?>/
    0.06
    �
    0.06
     Omaha
    0.06
     emitting
    0.06
     работ
    0.06
     MIN
    0.06
    Act Density 0.083%

    No Known Activations