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

    Neuronpedia

    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Negative Logits
    amel
    -0.26
    è¯Ĩ
    -0.25
    activities
    -0.25
    act
    -0.25
    ptive
    -0.24
    æ«ĥ
    -0.24
    æºIJæºIJ
    -0.24
    tdown
    -0.24
    æŁľåı°
    -0.24
    wright
    -0.24
    POSITIVE LOGITS
    @student
    0.33
    æķĻçłĶ
    0.27
    å§
    0.25
     yön
    0.24
    çŃ¾åŃĹ
    0.24
    Signed
    0.24
    æľªç»ı
    0.24
    oses
    0.23
     erot
    0.23
    osed
    0.23
    Act Density 0.000%

    No Known Activations

    This feature has no known activations.