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

    Neuronpedia

    INDEX
    Explanations

    programming with import statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.68
    Bes
    0.48
    os
    0.47
    Email
    0.46
    Login
    0.46
    login
    0.45
    成
    0.45
    email
    0.44
    Cas
    0.44
    Os
    0.43
    POSITIVE LOGITS
    环境变量
    0.47
    pInBuffer
    0.45
    轆
    0.45
    广播
    0.44
    电线路
    0.44
     candied
    0.43
     enfermos
    0.43
     archipelago
    0.42
     boucle
    0.42
    विध
    0.42
    Act Density 0.000%

    No Known Activations