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

    Neuronpedia

    INDEX
    Explanations

    fields are required

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Inactive
    0.45
    Investigation
    0.43
    )="
    0.43
    NewLine
    0.39
    AudioFocus
    0.39
    GROUP
    0.39
     INVENTION
    0.39
    NIS
    0.39
    ("-"
    0.38
    GroupName
    0.38
    POSITIVE LOGITS
    required
    0.82
     required
    0.76
     Required
    0.63
    trim
    0.61
     trim
    0.60
    Required
    0.59
     unique
    0.56
     REQUIRED
    0.56
     require
    0.55
     απαι
    0.54
    Act Density 0.005%

    No Known Activations