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

    Neuronpedia

    INDEX
    Explanations

    roles and profiles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    nej
    0.43
    anch
    0.40
    ended
    0.40
    ore
    0.39
     Length
    0.39
    arthen
    0.39
    clean
    0.39
    nych
    0.39
     Ank
    0.38
     lunghezza
    0.38
    POSITIVE LOGITS
     profile
    0.45
    profile
    0.40
     profiles
    0.40
     Profile
    0.38
    Profile
    0.38
     PROFILE
    0.38
     अवलोकन
    0.37
    Profiles
    0.37
     details
    0.35
    রত্ব
    0.35
    Act Density 0.000%

    No Known Activations