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

    Neuronpedia

    INDEX
    Explanations

    references to numerical values or measurements in scientific contexts

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

    numeric quantities with units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    OGND
    -0.93
     témoig
    -0.89
    <unused43>
    -0.85
    <unused79>
    -0.85
    <unused41>
    -0.85
    <unused16>
    -0.85
    <unused8>
    -0.85
    <unused14>
    -0.85
    <unused3>
    -0.85
    [@BOS@]
    -0.85
    POSITIVE LOGITS
     
    0.39
    ↵↵
    0.35
    ↵
    0.31
     e
    0.31
    Personensuche
    0.30
    0
    0.28
    ...
    0.27
     sarung
    0.26
    E
    0.26
     corrida
    0.25
    Act Density 0.026%

    No Known Activations