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

    Neuronpedia

    INDEX
    Explanations

    terms related to capabilities and features of systems or technologies

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

    capability or capable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <bos>
    -0.82
    js
    -0.43
     –
    -0.43
    st
    -0.42
    tr
    -0.42
     on
    -0.41
     or
    -0.41
     Stork
    -0.41
     texts
    -0.40
     s
    -0.40
    POSITIVE LOGITS
     Capability
    1.24
     Capabilities
    1.20
     capability
    1.19
    Capability
    1.17
    capability
    1.13
     capabilities
    1.08
    Capabilities
    1.07
    capabilities
    1.02
     Capa
    0.85
    capable
    0.77
    Act Density 0.008%

    No Known Activations