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

    Neuronpedia

    INDEX
    Explanations

    data transmission networks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rpt
    -0.08
    ��
    -0.07
    orado
    -0.07
    юсь
    -0.07
    反應
    -0.06
     cours
    -0.06
    auf
    -0.06
    齐
    -0.06
    �
    -0.06
     güç
    -0.06
    POSITIVE LOGITS
     wants
    0.08
     LABEL
    0.07
     whit
    0.07
     articles
    0.07
    (fake
    0.06
    Access
    0.06
    _DISCONNECT
    0.06
     Networking
    0.06
    _h
    0.06
    ㇺ
    0.06
    Act Density 0.043%

    No Known Activations