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

    Neuronpedia

    INDEX
    Explanations

    represent specific individuals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ۷
    0.45
    crib
    0.41
    Physics
    0.41
    ８
    0.41
    ٨
    0.41
    ٥
    0.40
    ೭
    0.39
    etheless
    0.39
    hierarchy
    0.38
    ٤
    0.38
    POSITIVE LOGITS
    ότερα
    0.42
    㘟
    0.42
    ังหว
    0.39
     newUser
    0.38
     repres
    0.38
     \\..
    0.38
     anticoagulant
    0.37
    JScripts
    0.37
     vapors
    0.36
     <%
    0.36
    Act Density 0.003%

    No Known Activations