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

    Neuronpedia

    INDEX
    Explanations

    cost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     BETWEEN
    -0.07
     FEATURE
    -0.07
    /session
    -0.07
     hd
    -0.06
    .names
    -0.06
     MACHINE
    -0.06
    /private
    -0.06
     masking
    -0.06
     notifications
    -0.06
     frightened
    -0.06
    POSITIVE LOGITS
    �
    0.07
    обра�
    0.07
     ADC
    0.07
    empor
    0.06
    อดภ
    0.06
    ΗΤ
    0.06
    Unfortunately
    0.06
    wart
    0.06
    няття
    0.06
    emoc
    0.06
    Act Density 0.012%

    No Known Activations