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

    Neuronpedia

    INDEX
    Explanations

    numerical units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     patronage
    0.43
    一定会
    0.39
    Narr
    0.38
    Nursing
    0.38
     Abdul
    0.37
     compet
    0.37
    Estimate
    0.36
     определён
    0.35
    rightarrow
    0.35
     curator
    0.35
    POSITIVE LOGITS
    となっている
    0.44
     centerY
    0.42
     contenant
    0.40
     kuris
    0.40
     printr
    0.40
     эта
    0.39
    </h1>
    0.39
     主要
    0.39
     並
    0.39
    yml
    0.38
    Act Density 0.001%

    No Known Activations