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

    Neuronpedia

    INDEX
    Explanations

    wealth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    جة
    -0.07
    drag
    -0.07
    ashed
    -0.07
    udem
    -0.07
     (“
    -0.07
     ("
    -0.06
    _submission
    -0.06
    인을
    -0.06
     �
    -0.06
    า
    -0.06
    POSITIVE LOGITS
    ."),↵
    0.06
    _GPS
    0.06
     saline
    0.06
    لال
    0.06
     elimin
    0.06
    (transaction
    0.06
     becoming
    0.06
    .travel
    0.06
    _named
    0.06
    	buf
    0.06
    Act Density 0.013%

    No Known Activations