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

    Neuronpedia

    INDEX
    Explanations

    Lev or Levy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nazw
    0.38
    ච
    0.36
    0.35
    চনার
    0.34
    visited
    0.34
    ходил
    0.34
    친
    0.34
     einzel
    0.34
    resource
    0.33
    ردم
    0.33
    POSITIVE LOGITS
     여
    0.42
     Levy
    0.40
     कॉन्
    0.40
     Levante
    0.39
    ודה
    0.38
    elisk
    0.38
     Leroy
    0.37
     salva
    0.37
     lev
    0.37
     लापरवाही
    0.36
    Act Density 0.001%

    No Known Activations