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

    Neuronpedia

    INDEX
    Explanations

    Email excerpts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _thumb
    -0.07
     Isn
    -0.07
    -arm
    -0.07
     weigh
    -0.07
     Kou
    -0.07
     COMMENT
    -0.06
     αρι
    -0.06
     lee
    -0.06
    _as
    -0.06
     Corn
    -0.06
    POSITIVE LOGITS
     supernatural
    0.07
     기억
    0.06
    Telefono
    0.06
    招聘
    0.06
     aantal
    0.06
    :title
    0.06
     minden
    0.06
     *)((
    0.06
    lijah
    0.06
    사랑
    0.06
    Act Density 0.031%

    No Known Activations