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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.88
     Administrativna
    -0.85
    <bos>
    -0.84
    expandindo
    -0.77
     تضيفلها
    -0.69
     kasarigan
    -0.66
    HostException
    -0.65
    aktery
    -0.65
    Portale
    -0.65
     AssemblyCulture
    -0.65
    POSITIVE LOGITS
     who
    0.62
    who
    0.57
     to
    0.45
    LookAnd
    0.44
    hålla
    0.44
     którzy
    0.43
    ∬
    0.42
    Who
    0.42
     Who
    0.40
    RectangleBorder
    0.39
    Act Density 0.017%

    No Known Activations