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

    Neuronpedia

    INDEX
    Explanations

    GUI, Lease, redirection, tires, bell

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    міст
    0.49
    開幕
    0.47
    omitempty
    0.46
     microsomal
    0.46
    Pasta
    0.46
    plaza
    0.45
    México
    0.44
     adhesion
    0.44
     NSUTF
    0.43
    ITest
    0.43
    POSITIVE LOGITS
    f
    0.47
     (
    0.44
     Recuer
    0.43
    <0xF0>
    0.42
    ই
    0.42
     up
    0.41
    o
    0.41
     ठेवा
    0.41
    之类的
    0.40
    →
    0.40
    Act Density 0.005%

    No Known Activations