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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     surv
    -0.32
    å¿ĥ缮
    -0.26
    è¨ĵ
    -0.26
    å½ĵä»Ĭ
    -0.25
    æħij
    -0.25
    èģ¿
    -0.24
    æļ´éľ²
    -0.24
    zew
    -0.24
    缮æłĩä»»åĬ¡
    -0.24
    ainment
    -0.24
    POSITIVE LOGITS
     October
    0.35
     September
    0.33
     April
    0.33
     July
    0.32
     November
    0.31
     June
    0.31
    tempt
    0.30
     February
    0.30
    Tu
    0.30
     December
    0.29
    Act Density 0.052%

    No Known Activations