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

    Neuronpedia

    INDEX
    Explanations

    differentiation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ο
    -0.08
     geschlossen
    -0.08
     κοινων
    -0.08
    .Mon
    -0.07
    ỗi
    -0.07
     آج
    -0.07
    ్చ
    -0.07
     Contrary
    -0.07
     வச
    -0.07
    Marketplace
    -0.07
    POSITIVE LOGITS
     continua
    0.09
    /controller
    0.08
     arrays
    0.08
     staffs
    0.08
    rae
    0.08
     yourself
    0.07
    hak
    0.07
     again
    0.07
     domanda
    0.07
     themselves
    0.07
    Act Density 0.008%

    No Known Activations