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

    Neuronpedia

    INDEX
    Explanations

    Code/encryption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     vowels
    -0.07
    ercise
    -0.07
    CSS
    -0.07
    ovation
    -0.07
    通信
    -0.07
    ино
    -0.06
    -modal
    -0.06
     ACL
    -0.06
    .additional
    -0.06
    אוכל
    -0.06
    POSITIVE LOGITS
    รม
    0.08
     Serializable
    0.08
     לי
    0.07
    んじゃないか
    0.07
    匣
    0.07
    發表
    0.07
    嫪
    0.07
    rite
    0.06
    _memcpy
    0.06
    ┻
    0.06
    Act Density 0.013%

    No Known Activations