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

    Neuronpedia

    INDEX
    Explanations

    (

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -cal
    -0.06
    +C
    -0.06
     Ae
    -0.06
     Lie
    -0.06
    .showMessage
    -0.06
     maduras
    -0.06
    	sp
    -0.06
    lineEdit
    -0.06
    maf
    -0.05
     mnoh
    -0.05
    POSITIVE LOGITS
     candle
    0.07
     neh
    0.07
     sensitive
    0.07
     tweak
    0.07
    orm
    0.07
    .tel
    0.07
     subsequent
    0.06
    .Enabled
    0.06
     nah
    0.06
    {\
    0.06
    Act Density 0.004%

    No Known Activations