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

    Neuronpedia

    INDEX
    Explanations

    collection

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blocks
    -0.07
     riders
    -0.07
     predecessor
    -0.06
     Gew
    -0.06
    věl
    -0.06
     ビ
    -0.06
    -actions
    -0.06
     counterpart
    -0.06
     domina
    -0.06
     rulers
    -0.06
    POSITIVE LOGITS
    殺
    0.07
    asy
    0.06
    овані
    0.06
     cout
    0.06
    onds
    0.06
     phot
    0.06
     moral
    0.06
     interpersonal
    0.06
    licative
    0.06
     DATE
    0.06
    Act Density 0.001%

    No Known Activations