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

    Neuronpedia

    INDEX
    Explanations

    references to interpersonal relationships and emotional connections

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

    pronouns followed by actions/states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    flags
    -0.41
    Flags
    -0.39
    flag
    -0.39
     flags
    -0.38
     connexes
    -0.37
     temu
    -0.37
     Entsch
    -0.37
    ENES
    -0.36
     pos
    -0.36
     termica
    -0.36
    POSITIVE LOGITS
    tagext
    0.63
     CreateTagHelper
    0.54
     препратки
    0.53
     Италијани
    0.49
    WireFormatLite
    0.48
    ſelf
    0.47
     queſta
    0.47
    Архівовано
    0.45
     GetEnumerator
    0.44
     MainAxisSize
    0.44
    Act Density 0.083%

    No Known Activations