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

    Neuronpedia

    INDEX
    Explanations

    code and technical documentation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	bs
    -0.07
    OCK
    -0.06
    _username
    -0.06
    ασ
    -0.06
     grounding
    -0.06
     Beta
    -0.06
     вос
    -0.06
    _ter
    -0.06
    izr
    -0.06
    eldon
    -0.06
    POSITIVE LOGITS
    
    0.06
    ाड
    0.06
     framed
    0.06
     swept
    0.06
    .Op
    0.06
    창
    0.06
     torchvision
    0.06
     огром
    0.06
    typeof
    0.06
     полез
    0.06
    Act Density 0.180%

    No Known Activations