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

    Neuronpedia

    INDEX
    Explanations

    astrological signs and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    দন্ত
    0.53
    Germany
    0.53
    殮
    0.51
    CONTAIN
    0.49
    hôpital
    0.49
    ದ್ರ
    0.48
    ДС
    0.46
     основ
    0.46
    Ста
    0.46
     ufficiale
    0.46
    POSITIVE LOGITS
     Hello
    0.52
     Abraham
    0.47
    0.45
     further
    0.44
     Schr
    0.44
     De
    0.43
     Albert
    0.43
     Sh
    0.43
     begins
    0.43
     manures
    0.42
    Act Density 0.005%

    No Known Activations