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

    Neuronpedia

    INDEX
    Explanations

    sharing experiences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     RegExp
    0.99
     Aliens
    0.98
    кого
    0.95
    یتی
    0.92
     Caves
    0.91
     Bxd
    0.91
    鹂
    0.90
    WebGL
    0.89
    interrupt
    0.88
     responde
    0.88
    POSITIVE LOGITS
    cropping
    1.38
     experiences
    1.25
     expériences
    1.13
     experiências
    1.10
    rä
    1.09
    experiences
    1.05
     vulner
    1.05
    vigor
    1.05
     responsibility
    1.04
     sare
    1.04
    Act Density 0.043%

    No Known Activations