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

    Neuronpedia

    INDEX
    Explanations

    website code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ḁ
    -0.07
    ,Th
    -0.06
    껄
    -0.06
     tú
    -0.06
    ݒ
    -0.06
    �
    -0.06
    ,</
    -0.06
     Waters
    -0.06
    ↵↵    ↵
    -0.06
    밭
    -0.06
    POSITIVE LOGITS
     Christian
    0.08
     earlier
    0.08
    .java
    0.07
     tougher
    0.07
    .nano
    0.07
    len
    0.07
     older
    0.07
    rog
    0.06
    对应
    0.06
     multip
    0.06
    Act Density 0.000%

    No Known Activations