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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     finest
    -0.07
     Cic
    -0.06
     Colbert
    -0.06
    ি
    -0.06
     �
    -0.06
     damages
    -0.06
    (document
    -0.06
     chatter
    -0.06
     OTP
    -0.06
    -brand
    -0.06
    POSITIVE LOGITS
    &o
    0.07
     otros
    0.06
    Pedido
    0.06
    ae
    0.06
    ागर
    0.06
    ự
    0.06
    boy
    0.06
    .mp
    0.06
    amped
    0.06
    iah
    0.06
    Act Density 0.085%

    No Known Activations