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

    Neuronpedia

    INDEX
    Explanations

    saying yes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    称为
    0.38
     customizable
    0.36
    ರುತ್ತವೆ
    0.33
     depot
    0.32
     selected
    0.32
     Bef
    0.31
     bef
    0.31
    ினர்
    0.30
     વિવિધ
    0.30
     depots
    0.30
    POSITIVE LOGITS
     yeah
    0.59
    yeah
    0.55
    Yeah
    0.53
     Yeah
    0.49
     এটা
    0.45
     बेसिकली
    0.45
     ahorita
    0.44
     ரொம்ப
    0.44
     люди
    0.44
     যেটা
    0.43
    Act Density 0.077%

    No Known Activations