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

    Neuronpedia

    INDEX
    Explanations

    discussions about disassembly and assembly processes

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

    things breaking or getting worse

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ➯
    -0.64
    riwal
    -0.57
    -0.56
    ReusableCell
    -0.47
    ----</
    -0.46
     Italijanski
    -0.46
    OGND
    -0.45
     forfeiture
    -0.45
    MessageOf
    -0.44
    AndEndTag
    -0.43
    POSITIVE LOGITS
    middels
    0.41
     espresso
    0.40
     nového
    0.39
    espresso
    0.37
    JNIEnv
    0.37
    VersionUID
    0.36
    Datuak
    0.35
     Regelung
    0.35
     Zähne
    0.34
     Veränderungen
    0.34
    Act Density 0.059%

    No Known Activations