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

    Neuronpedia

    INDEX
    Explanations

    famous last names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     це
    0.43
     concealment
    0.41
     skim
    0.38
    oretically
    0.37
     consonant
    0.37
     variational
    0.37
    Begin
    0.36
    J
    0.36
     알
    0.36
    OP
    0.36
    POSITIVE LOGITS
    âns
    0.58
    oury
    0.53
    ánico
    0.49
    leston
    0.49
    âge
    0.48
    anners
    0.47
    länder
    0.47
    ágico
    0.46
    aski
    0.45
    ié
    0.45
    Act Density 0.051%

    No Known Activations