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

    Neuronpedia

    INDEX
    Explanations

    technical documentation links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     subj
    0.39
     Trafalgar
    0.38
     BlueprintName
    0.37
     fragment
    0.37
     OX
    0.37
    ρές
    0.37
    FRAGMENT
    0.37
     remnant
    0.36
     furtherance
    0.36
     enlightening
    0.35
    POSITIVE LOGITS
    ぉ
    0.47
    abend
    0.45
    includ
    0.40
     принци
    0.40
    𝘋
    0.39
    motivation
    0.39
    iswa
    0.38
    cystic
    0.38
     vuccati
    0.38
     stwier
    0.38
    Act Density 0.000%

    No Known Activations