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

    Neuronpedia

    INDEX
    Explanations

    `hyperref` and replace placeholders

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    リーブ
    0.42
    otoxin
    0.38
    pairing
    0.37
    _{+}+
    0.37
     unha
    0.37
     tristeza
    0.37
     Negra
    0.36
     weep
    0.36
    ္ဂ
    0.36
     rejo
    0.36
    POSITIVE LOGITS
     Hyp
    0.79
     हाइ
    0.78
    Hyper
    0.77
    Hyp
    0.76
    hyp
    0.74
     hy
    0.71
     hyp
    0.71
    hyper
    0.70
     Hyper
    0.69
    HY
    0.68
    Act Density 0.005%

    No Known Activations