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

    Neuronpedia

    INDEX
    Explanations

    nestled amongst, deep in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Realtor
    0.74
     clots
    0.69
    گار
    0.68
     inhibited
    0.68
     προϊόν
    0.67
     seguros
    0.67
    \<^
    0.67
    0.66
     estar
    0.65
     priors
    0.65
    POSITIVE LOGITS
    side
    0.65
    sides
    0.61
    supp
    0.58
    sand
    0.54
    s
    0.53
    1
    0.52
    yield
    0.50
    তম
    0.50
    Imperial
    0.50
    git
    0.50
    Act Density 0.302%

    No Known Activations