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

    Neuronpedia

    INDEX
    Explanations

    Lists of different things

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (required
    -0.07
    .Te
    -0.07
    กำหน
    -0.07
    śli
    -0.07
    [np
    -0.06
    قلق
    -0.06
     regardless
    -0.06
    �
    -0.06
    laşma
    -0.06
    老子
    -0.06
    POSITIVE LOGITS
     Thumbnails
    0.07
    病毒感染
    0.07
    Bank
    0.07
     Kod
    0.07
     JOHN
    0.07
    IDs
    0.07
    Picker
    0.07
    suffix
    0.07
    vf
    0.07
    SIDE
    0.07
    Act Density 0.168%

    No Known Activations