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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ADOS
    -0.28
    ados
    -0.27
    aptor
    -0.27
    å¤ļä½į
    -0.27
    anium
    -0.25
    æĢ»
    -0.25
    åĪ°åºķ
    -0.25
    DED
    -0.25
     president
    -0.24
     Mehr
    -0.24
    POSITIVE LOGITS
    renc
    0.27
    osten
    0.27
    resh
    0.26
     tails
    0.25
    .inc
    0.25
    ré
    0.25
    _TRUNC
    0.25
     Belg
    0.24
    tail
    0.24
    å°¾
    0.24
    Act Density 0.063%

    No Known Activations