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

    Neuronpedia

    INDEX
    Explanations

    proteins, biological, values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     réc
    0.50
     seals
    0.50
     newfound
    0.49
     blocks
    0.47
     skepticism
    0.47
     kisah
    0.47
     f
    0.46
     contagion
    0.46
     daftar
    0.46
     spans
    0.45
    POSITIVE LOGITS
    Tim
    0.53
    Ви
    0.51
    ."[
    0.51
    attro
    0.47
    .");
    0.46
    larak
    0.46
    лизова
    0.46
    .")
    0.45
    sime
    0.44
    Ро
    0.44
    Act Density 0.003%

    No Known Activations