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

    Neuronpedia

    INDEX
    Explanations

    terminology related to memory layout and stride configurations in programming

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

    movement and physics symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Administrativna
    -0.61
    UserScript
    -0.49
     informée
    -0.46
     Infórmanos
    -0.46
     roman
    -0.45
     Vac
    -0.43
     autorytatywna
    -0.43
    Gesam
    -0.41
     elettron
    -0.40
     Vlas
    -0.40
    POSITIVE LOGITS
     stride
    2.45
    stride
    2.19
    Stride
    1.96
     strides
    1.88
    strides
    1.69
     strode
    1.11
     Stri
    0.88
     Stroll
    0.82
     stroll
    0.75
     strive
    0.74
    Act Density 0.006%

    No Known Activations