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

    Neuronpedia

    INDEX
    Explanations

    contradictions/qualifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    utorial
    -0.07
     Johnson
    -0.07
     ul
    -0.06
     judicial
    -0.06
    navbarSupportedContent
    -0.06
     Transmit
    -0.06
    voice
    -0.06
    ReceiveMemoryWarning
    -0.06
    Conta
    -0.06
     تم
    -0.06
    POSITIVE LOGITS
    _FOUND
    0.07
     Boris
    0.06
    เ�
    0.06
    boro
    0.06
    _was
    0.06
    _logs
    0.06
    textbox
    0.06
    _assignment
    0.06
     refund
    0.06
     marched
    0.06
    Act Density 0.047%

    No Known Activations