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

    Neuronpedia

    INDEX
    Explanations

    terms related to upward movement or direction

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

    upward direction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    oflavin
    -0.59
    \{\\
    -0.57
     StringTokenizer
    -0.56
    acamata
    -0.56
    addContainerGap
    -0.55
     témoig
    -0.54
    zzlies
    -0.53
     Roskov
    -0.53
    Parcelize
    -0.53
    IBLIO
    -0.53
    POSITIVE LOGITS
     upward
    1.88
     downward
    1.55
     upwards
    1.46
     downwards
    1.22
     outward
    1.09
     inward
    1.01
     northward
    1.00
    ward
    0.97
     onward
    0.95
     southward
    0.91
    Act Density 0.010%

    No Known Activations