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

    Neuronpedia

    INDEX
    Explanations

    dynamic changes in conditions or states

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

    fall, decrease, collapse, explode

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     препратки
    -0.54
    awtextra
    -0.54
     
    -0.54
    omie
    -0.50
    deepcopy
    -0.49
     tribu
    -0.47
    Personendaten
    -0.47
     esternos
    -0.46
     vase
    -0.45
    )‏
    -0.45
    POSITIVE LOGITS
     eléctricas
    0.52
     literario
    0.49
     tumbuh
    0.47
     femeninos
    0.46
     cromado
    0.46
     aisladas
    0.45
     históricas
    0.44
     aspetta
    0.44
     pintado
    0.43
     aéro
    0.43
    Act Density 0.241%

    No Known Activations