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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
     Sins
    -0.67
     Vale
    -0.65
    Va
    -0.62
    driving
    -0.61
     Noir
    -0.61
     Avenger
    -0.61
     valley
    -0.60
     MH
    -0.60
    grain
    -0.59
     Drawn
    -0.59
    POSITIVE LOGITS
    ²¾
    0.92
    £ı
    0.88
    aptic
    0.84
    ¶ħ
    0.81
     srfAttach
    0.79
    ategory
    0.74
    ĵĺ
    0.71
    ĨĴ
    0.67
    ucket
    0.67
     ledge
    0.67
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.