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

    Neuronpedia

    INDEX
    Explanations

    code identifiers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    HorizontalAlignment
    -0.06
    :host
    -0.06
     Purple
    -0.06
     defining
    -0.06
     performed
    -0.06
    	height
    -0.06
    起来
    -0.06
     ü
    -0.06
     IsNot
    -0.06
    Employees
    -0.06
    POSITIVE LOGITS
    ١
    0.07
     Vad
    0.07
    верд
    0.06
    슈
    0.06
     모르
    0.06
     Nun
    0.06
    ิโน
    0.06
    Za
    0.06
    \Carbon
    0.06
     нік
    0.06
    Act Density 0.024%

    No Known Activations