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

    Neuronpedia

    INDEX
    Explanations

    systems and methods embodying options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Eso
    0.43
     그걸
    0.43
     participant
    0.42
     toucher
    0.41
    participant
    0.41
     artístico
    0.40
     device
    0.40
     이걸
    0.40
     จำ
    0.38
     সবাই
    0.38
    POSITIVE LOGITS
     Various
    0.59
     Certain
    0.53
     Preferably
    0.53
     preferably
    0.50
     certain
    0.49
     Alternate
    0.49
    preferably
    0.49
     Either
    0.49
     An
    0.48
     Optionally
    0.48
    Act Density 0.002%

    No Known Activations