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

    Neuronpedia

    INDEX
    Explanations

    series

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    PBS
    -0.06
    477
    -0.06
    细
    -0.06
    Psi
    -0.06
    raft
    -0.06
     fire
    -0.06
     nhiễm
    -0.06
     NGO
    -0.06
     Angie
    -0.06
     puss
    -0.06
    POSITIVE LOGITS
     Lights
    0.08
     Series
    0.06
     passive
    0.06
    achusetts
    0.06
     Quar
    0.06
    "]){↵
    0.06
     recipient
    0.06
     ceil
    0.06
     bufferSize
    0.06
     hindsight
    0.06
    Act Density 0.024%

    No Known Activations