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

    Neuronpedia

    INDEX
    Explanations

    Technical/scientific documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pieces
    -0.30
     Apprent
    -0.27
     puck
    -0.26
    ŃIJ
    -0.26
    appropri
    -0.26
     Positive
    -0.25
     blast
    -0.25
    andle
    -0.24
    ollect
    -0.24
    è¿Ļä¸ĢçĤ¹
    -0.24
    POSITIVE LOGITS
    æķĮ
    0.28
    dff
    0.28
    jango
    0.27
    è¾IJ
    0.26
    .freq
    0.26
    ady
    0.26
    åŃĹæ¯į
    0.25
    freq
    0.25
    ç¼Ģ
    0.25
     jur
    0.24
    Act Density 1.133%

    No Known Activations