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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate requirements or necessities related to actions or tasks

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

    need to do something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Chwiliwch
    -0.69
     esternos
    -0.51
     kasarigan
    -0.50
    matchCondition
    -0.49
    Notae
    -0.48
    ſelves
    -0.48
    ſelf
    -0.47
     Buf
    -0.47
    ("}\
    -0.46
    ########.
    -0.46
    POSITIVE LOGITS
    ✭✭
    0.42
    ẹo
    0.41
     square
    0.41
     nahilalakip
    0.40
     iprot
    0.38
    RefNanny
    0.37
     Normdatei
    0.37
     Schatz
    0.36
     Príncipe
    0.35
    Cyfarwyddwr
    0.35
    Act Density 0.053%

    No Known Activations