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

    Neuronpedia

    INDEX
    Explanations

    css list styling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    cest
    0.52
     основу
    0.51
    eworld
    0.49
    tä
    0.49
    wares
    0.47
    álise
    0.47
    ets
    0.47
    udades
    0.46
    anum
    0.46
    urses
    0.46
    POSITIVE LOGITS
     criminal
    0.52
     los
    0.50
     There
    0.50
     regression
    0.50
     falls
    0.49
     mountain
    0.48
     winning
    0.47
     good
    0.47
    ρών
    0.46
     rock
    0.46
    Act Density 0.000%

    No Known Activations