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

    Neuronpedia

    INDEX
    Explanations

    comment blocks in code

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

    #endif comments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     <<<<<<<<<<<<<<
    -0.39
     Innenstadt
    -0.33
    ]='\
    -0.31
     localizar
    -0.28
     обращения
    -0.28
    setVerticalGroup
    -0.28
    /**
    -0.27
    μένος
    -0.27
    OGND
    -0.27
    一
    -0.27
    POSITIVE LOGITS
    Builder
    1.05
     Builder
    0.84
     BUILD
    0.77
     builder
    0.76
    builder
    0.76
     newBuilder
    0.67
     build
    0.62
     builders
    0.62
     jspb
    0.61
    iſen
    0.60
    Act Density 0.001%

    No Known Activations