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

    Neuronpedia

    INDEX
    Explanations

    phrases related to rounding numbers or mathematical approximations

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

    rounding to nearest place

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.65
     esternos
    -0.63
    __':
    -0.59
    AndEndTag
    -0.57
    Искәрмәләр
    -0.55
    MessageOf
    -0.53
    ThroughAttribute
    -0.52
    __":
    -0.51
    __":
    -0.51
    localctx
    -0.51
    POSITIVE LOGITS
     rounding
    0.48
    に近い
    0.43
     redonde
    0.43
    NEAR
    0.40
     nearest
    0.40
    nearest
    0.40
    pgterms
    0.40
     accuracy
    0.39
     nearer
    0.39
     aproxim
    0.38
    Act Density 0.040%

    No Known Activations