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

    Neuronpedia

    INDEX
    Explanations

    entry conditions and relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    0.49
    invoice
    0.48
    gever
    0.48
    ｎ
    0.48
    ў
    0.48
     అక్క
    0.48
    chromium
    0.47
    very
    0.47
    нес
    0.46
    ᆸ
    0.45
    POSITIVE LOGITS
     menet
    0.44
     Mutant
    0.44
     Relationships
    0.43
     spineItem
    0.43
     relationships
    0.42
     Death
    0.42
     larch
    0.42
    Death
    0.41
     advising
    0.39
    苼
    0.39
    Act Density 0.004%

    No Known Activations