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

    Neuronpedia

    INDEX
    Explanations

    handed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ç§ĭ
    -0.28
    ç§ĭ天
    -0.28
    horn
    -0.28
     oct
    -0.27
     Oct
    -0.27
     refresh
    -0.26
    è°
    -0.26
    æ®ĸæ°ij
    -0.26
    Oct
    -0.26
    宫
    -0.25
    POSITIVE LOGITS
    èĭ¦
    0.27
    åĬŁè¯¾
    0.27
     nostalg
    0.26
    aber
    0.26
    LEM
    0.25
     Budd
    0.25
     Padres
    0.25
    versions
    0.25
    atin
    0.24
    è¾ij
    0.24
    Act Density 0.117%

    No Known Activations