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

    Neuronpedia

    INDEX
    Explanations

    memory recall

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dospěl
    -0.06
     triples
    -0.06
     تاب
    -0.06
     nejvyšší
    -0.06
    character
    -0.06
     �
    -0.06
    _invoke
    -0.06
     topology
    -0.06
    ablo
    -0.06
    ˆ
    -0.06
    POSITIVE LOGITS
    camel
    0.07
     recall
    0.06
     garner
    0.06
    getColor
    0.06
    fef
    0.06
     spons
    0.06
    htags
    0.06
     Anh
    0.06
    ="#"
    0.06
     honoured
    0.06
    Act Density 0.477%

    No Known Activations