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

    Neuronpedia

    INDEX
    Explanations

    start of actions or processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     когато
    0.59
     ומ
    0.57
    ግሎ
    0.56
    veloc
    0.55
     commerciales
    0.54
     второго
    0.53
    tls
    0.53
     һәм
    0.52
     және
    0.52
     uvijek
    0.52
    POSITIVE LOGITS
     increasingly
    0.50
     passing
    0.47
     nuanced
    0.46
     deliberate
    0.45
     appealing
    0.45
     refined
    0.44
     qualitatively
    0.44
     extensively
    0.43
     a
    0.42
     stumbling
    0.42
    Act Density 0.024%

    No Known Activations