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

    Neuronpedia

    INDEX
    Explanations

    .h

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _attached
    -0.07
    яч
    -0.07
     دنیا
    -0.07
    131
    -0.06
    dae
    -0.06
     امر
    -0.06
     stringWith
    -0.06
    ‪
    -0.06
     جمهوری
    -0.06
    روط
    -0.06
    POSITIVE LOGITS
     maneuver
    0.07
    oth
    0.06
    emat
    0.06
    .jsx
    0.06
    -h
    0.06
    Callable
    0.06
     concentr
    0.06
     Married
    0.06
    	
↵
    0.06
    /entity
    0.06
    Act Density 0.001%

    No Known Activations