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

    Neuronpedia

    INDEX
    Explanations

    little bit

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    xml
    0.44
    as
    0.43
    set
    0.41
    collider
    0.40
    Floating
    0.39
    text
    0.38
     xml
    0.38
     decimal
    0.38
    total
    0.37
    at
    0.37
    POSITIVE LOGITS
    傕
    0.48
    テレ
    0.40
    တိ
    0.40
     obtains
    0.37
    estries
    0.37
     emigrated
    0.37
     tardes
    0.36
    νει
    0.36
    䄳
    0.36
    ㄈ
    0.36
    Act Density 0.001%

    No Known Activations