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

    Neuronpedia

    INDEX
    Explanations

    variable assignments in code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াড়ার
    0.33
    र्दशी
    0.33
    盈利
    0.32
    νοντας
    0.32
     Boyfriend
    0.32
    癃
    0.32
    iftoire
    0.31
    ্সে
    0.31
    getRedTeam
    0.31
    佻
    0.31
    POSITIVE LOGITS
     =
    0.38
     formalism
    0.33
    ː
    0.33
     MeV
    0.33
     t
    0.32
     ln
    0.32
     auton
    0.32
     इसको
    0.32
     Mathematic
    0.31
    _
    0.31
    Act Density 0.000%

    No Known Activations