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

    Neuronpedia

    INDEX
    Explanations

    specific data model definitions in code

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

    database field types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ice
    -0.38
    ″]
    -0.36
    чего
    -0.32
     hypo
    -0.31
     OMITBAD
    -0.31
     mine
    -0.30
     onto
    -0.30
     gesehen
    -0.29
    (">>
    -0.29
     brothers
    -0.29
    POSITIVE LOGITS
    CharField
    4.84
    IntegerField
    1.65
    ImageField
    1.48
    DateTimeField
    1.48
    AutoField
    1.42
    DateField
    1.22
    FloatField
    1.20
    BooleanField
    1.16
     StringField
    1.11
    makeText
    0.99
    Act Density 0.002%

    No Known Activations