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

    Neuronpedia

    INDEX
    Explanations

    HTML tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    OSH
    -0.06
    сов
    -0.06
     Cause
    -0.06
    Sp
    -0.06
    _comm
    -0.06
    ンダ
    -0.06
    HAL
    -0.05
     calories
    -0.05
    EmptyEntries
    -0.05
     Tob
    -0.05
    POSITIVE LOGITS
     Allocation
    0.07
     Twins
    0.07
     Sparks
    0.07
    .viewport
    0.07
     unleashed
    0.06
     meddling
    0.06
     العمل
    0.06
     elimination
    0.06
     이상
    0.06
    	spec
    0.06
    Act Density 0.005%

    No Known Activations