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

    Neuronpedia

    INDEX
    Explanations

    increasing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    isValid
    -0.07
    accessible
    -0.07
     Carn
    -0.07
     dl
    -0.06
     leveling
    -0.06
     Van
    -0.06
    pend
    -0.06
    497
    -0.06
    Dto
    -0.06
    counter
    -0.06
    POSITIVE LOGITS
     появ
    0.06
    �
    0.06
    并不
    0.06
     unfolded
    0.06
    _geometry
    0.06
     йому
    0.06
    Advertisements
    0.06
    .outputs
    0.06
     pornos
    0.06
     квар
    0.06
    Act Density 0.048%

    No Known Activations