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

    Neuronpedia

    INDEX
    Explanations

    phrasings related to limitations and accessibility

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

    "reach" or "reachable"

    np_acts-logits-general · gemini-2.0-flash

    out of reach

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     val
    -0.41
     Jam
    -0.40
    lats
    -0.40
    glLoadIdentity
    -0.40
     IEnumerator
    -0.39
     BorderLayout
    -0.39
     سكانية
    -0.39
    umn
    -0.38
    [:]
    -0.38
    val
    -0.37
    POSITIVE LOGITS
     reachable
    1.52
     reach
    1.40
     Reach
    1.37
     unreachable
    1.29
    Reach
    1.27
     attainable
    1.24
    reach
    1.21
     reaches
    1.13
    reachable
    1.13
     achievable
    1.12
    Act Density 0.133%

    No Known Activations