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

    Neuronpedia

    INDEX
    Explanations

    Preparing for public speaking

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     menj
    -0.08
     �
    -0.08
     Poss
    -0.07
     gev
    -0.07
     lettuce
    -0.07
    anches
    -0.07
     tube
    -0.06
    .sp
    -0.06
    ㄟ
    -0.06
    --)↵
    -0.06
    POSITIVE LOGITS
    PART
    0.08
    _REPLY
    0.07
    甘
    0.07
    注册
    0.07
    一幅
    0.07
    .are
    0.07
     definit
    0.06
    半岛
    0.06
    Act
    0.06
    حديث
    0.06
    Act Density 0.051%

    No Known Activations