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

    Neuronpedia

    INDEX
    Explanations

    play

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .GetSize
    -0.07
     assertions
    -0.07
     сент
    -0.07
     CCT
    -0.07
    .D
    -0.07
    客户端
    -0.06
    .Per
    -0.06
    前列腺
    -0.06
     School
    -0.06
    seg
    -0.06
    POSITIVE LOGITS
    blocking
    0.08
     FORCE
    0.07
     sunk
    0.07
    Jose
    0.07
     loose
    0.07
     potency
    0.07
    늬
    0.07
    .fail
    0.07
     chiar
    0.07
    .attach
    0.07
    Act Density 0.030%

    No Known Activations