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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _STATS
    -0.09
    _BUFFER
    -0.08
    _ACCESS
    -0.08
    _DIG
    -0.08
    _PIPE
    -0.08
    .freq
    -0.07
    -solving
    -0.07
    _FREQ
    -0.07
    Replacing
    -0.07
     permettant
    -0.07
    POSITIVE LOGITS
     assurances
    0.10
     phrases
    0.09
     강조
    0.09
     Assurance
    0.09
     assurance
    0.09
     disclaimer
    0.09
     disclaim
    0.08
     keywords
    0.08
     ঘোষণা
    0.08
     বাক
    0.08
    Act Density 0.003%

    No Known Activations