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

    Neuronpedia

    INDEX
    Explanations

    patterns related to URLs or account recovery codes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    k / К

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     uitz
    -0.46
    ьаж
    -0.42
     Ayuda
    -0.40
     Erwin
    -0.40
     holand
    -0.39
     Kebijakan
    -0.39
     doInBackground
    -0.39
     viewDidLoad
    -0.38
     Satz
    -0.38
     wyda
    -0.38
    POSITIVE LOGITS
    ůli
    0.57
    К
    0.56
     surla
    0.55
    AndEndTag
    0.52
    inear
    0.51
    évaluateur
    0.50
     К
    0.50
    Towards
    0.49
     COB
    0.49
    rrggbb
    0.48
    Act Density 0.013%

    No Known Activations