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

    Neuronpedia

    INDEX
    Explanations

    treaty

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     choir
    -0.07
    元
    -0.06
    payload
    -0.06
     Charges
    -0.06
     元
    -0.06
     Grove
    -0.06
    jwt
    -0.06
    factor
    -0.06
     dissect
    -0.06
    "):↵
    -0.06
    POSITIVE LOGITS
    perfil
    0.07
    �
    0.07
    invest
    0.07
                                                    ↵
    0.07
    iless
    0.06
    (pr
    0.06
    Lista
    0.06
     abrasive
    0.06
     عمر
    0.06
    pub
    0.06
    Act Density 0.010%

    No Known Activations