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

    Neuronpedia

    INDEX
    Explanations

    code/logs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     friday
    -0.07
    setMessage
    -0.07
     ctx
    -0.07
    .vn
    -0.07
    Ctl
    -0.06
     Disabled
    -0.06
    ละ
    -0.06
     Doug
    -0.06
     عندما
    -0.06
     plug
    -0.06
    POSITIVE LOGITS
    ecut
    0.07
     Kendrick
    0.07
    olvimento
    0.07
    pciones
    0.06
     earners
    0.06
    روش
    0.06
    tain
    0.06
     Tata
    0.06
     nær
    0.06
     heating
    0.06
    Act Density 0.000%

    No Known Activations