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

    Neuronpedia

    INDEX
    Explanations

    soft

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    570
    -0.07
    ออก
    -0.07
     priceless
    -0.07
     Booth
    -0.06
    Wildcard
    -0.06
    četně
    -0.06
     NCAA
    -0.06
     HW
    -0.06
     escalate
    -0.06
    】【
    -0.06
    POSITIVE LOGITS
     insecurity
    0.07
    -event
    0.06
    手を
    0.06
     Fen
    0.06
     druh
    0.06
     �
    0.06
    .getAccount
    0.06
     weakness
    0.06
    reno
    0.06
     flex
    0.06
    Act Density 0.006%

    No Known Activations