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

    Neuronpedia

    INDEX
    Explanations

    is

    np_max-act · gemini-2.0-flash

    is

    np_max-act-logits · gpt-5-miniTriggered by @chenshw0109
    New Auto-Interp
    Negative Logits
     is
    -2.00
     has
    -1.01
     are
    -0.84
     was
    -0.84
     can
    -0.77
     Is
    -0.75
     will
    -0.73
    is
    -0.72
     isn
    -0.72
     may
    -0.69
    POSITIVE LOGITS
     myſelf
    1.16
     ſaid
    1.11
     ſmall
    1.10
     uſed
    1.09
     raiſ
    1.08
     leſs
    1.08
    Personendaten
    1.08
     purpoſe
    1.06
    Personensuche
    1.05
     poffe
    1.05
    Act Density 0.802%

    No Known Activations