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

    Neuronpedia

    INDEX
    Explanations

    teams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    j
    -0.49
     or
    -0.49
    z
    -0.46
    my
    -0.46
     l
    -0.44
    ...
    -0.43
    p
    -0.43
    l
    -0.43
    ca
    -0.43
    we
    -0.43
    POSITIVE LOGITS
     pinulongan
    1.34
     Efq
    1.22
    ſelf
    1.22
     myſelf
    1.16
     themſelves
    1.15
     Monfieur
    1.13
     pleaſure
    1.07
    ⓧ
    1.05
     Majefty
    1.05
    ſelves
    1.05
    Act Density 0.000%

    No Known Activations