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

    Neuronpedia

    INDEX
    Explanations

    expressions of doubt or insecurity

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

    insecure, leather

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.66
     initComponents
    -0.56
     ligiloj
    -0.52
    Leve
    -0.51
    uxxxx
    -0.48
     Leve
    -0.47
    GEBURTSDATUM
    -0.46
     Infórmanos
    -0.45
     Signalez
    -0.45
     للاسماء
    -0.44
    POSITIVE LOGITS
    раздо
    0.43
    mergeFrom
    0.40
     Türen
    0.39
     Baer
    0.38
     noDo
    0.37
     pungkasnya
    0.37
     Erickson
    0.37
     construcciones
    0.37
     Anwendungen
    0.36
     berdua
    0.36
    Act Density 0.215%

    No Known Activations