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

    Neuronpedia

    INDEX
    Explanations

    best

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    xde
    -0.07
     Fleming
    -0.06
    oble
    -0.06
    DbContext
    -0.06
    (None
    -0.06
    xFF
    -0.06
    Particles
    -0.06
    _TEM
    -0.06
     prisoners
    -0.06
    (headers
    -0.06
    POSITIVE LOGITS
    )(__
    0.06
     때문에
    0.06
    �
    0.06
     misconception
    0.06
     FIRST
    0.06
     Golden
    0.06
    ()?
    0.06
     बन
    0.06
     rõ
    0.06
     argv
    0.06
    Act Density 0.007%

    No Known Activations