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

    Neuronpedia

    INDEX
    Explanations

    positive and qualitative descriptors related to experiences or products

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

    descriptive statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Opiniones
    -0.41
     Namun
    -0.40
     naselje
    -0.36
     however
    -0.36
     entanto
    -0.36
     podjet
    -0.35
     first
    -0.35
     palavra
    -0.34
     informação
    -0.34
     vandaag
    -0.34
    POSITIVE LOGITS
    tagHelperRunner
    0.60
     autorytatywna
    0.59
    出版年
    0.57
     estekak
    0.57
    何より
    0.56
    MigrationBuilder
    0.52
    SequentialGroup
    0.52
    OGND
    0.49
     ***!
    0.49
    dAtA
    0.47
    Act Density 0.025%

    No Known Activations