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

    Neuronpedia

    INDEX
    Explanations

    handling asynchronous results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ovec
    0.42
    过度
    0.39
     denke
    0.39
    0.38
    ļa
    0.37
     Jackman
    0.37
     vet
    0.37
    eral
    0.36
    Lose
    0.36
    ില്ല
    0.36
    POSITIVE LOGITS
     THEN
    0.74
     then
    0.72
    then
    0.71
     τότε
    0.67
     Then
    0.66
     entonces
    0.66
     whereupon
    0.61
    Then
    0.61
     allora
    0.61
     então
    0.59
    Act Density 0.009%

    No Known Activations