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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    acies
    -0.83
    thur
    -0.83
    Ĥİ
    -0.67
    ĺħ
    -0.65
    aura
    -0.63
    ²¾
    -0.62
     Domain
    -0.61
    scale
    -0.61
    ntil
    -0.61
     Cancel
    -0.60
    POSITIVE LOGITS
    Sab
    0.74
     Kling
    0.71
    ilic
    0.71
    Leaks
    0.68
    IFE
    0.67
    pee
    0.65
    XY
    0.64
    YP
    0.63
    Sel
    0.62
    Ingredients
    0.60
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.