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

    Neuronpedia

    INDEX
    Explanations

    ooo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     entrepreneur
    -0.07
     continuously
    -0.07
     evacuate
    -0.07
     postpon
    -0.07
    tility
    -0.06
    -make
    -0.06
     plunder
    -0.06
    uros
    -0.06
    arie
    -0.06
     Elevated
    -0.06
    POSITIVE LOGITS
    ±n
    0.07
     ku
    0.07
     vej
    0.07
     Verd
    0.06
    _accept
    0.06
    일에
    0.06
    larını
    0.06
     omega
    0.06
     PACKET
    0.06
    COND
    0.06
    Act Density 0.007%

    No Known Activations