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

    Neuronpedia

    INDEX
    Explanations

    immediate willingness

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Prometheus
    -0.07
    Join
    -0.07
    resi
    -0.06
    Printer
    -0.06
    อำ
    -0.06
    Democratic
    -0.06
    Execute
    -0.06
    -${
    -0.06
    θε
    -0.06
    Democrats
    -0.06
    POSITIVE LOGITS
     Gina
    0.07
    .CLASS
    0.07
     fashioned
    0.07
     Craft
    0.06
     unusual
    0.06
     밀
    0.06
     received
    0.06
     al
    0.06
    obox
    0.06
    _IGNORE
    0.06
    Act Density 0.028%

    No Known Activations