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

    Neuronpedia

    INDEX
    Explanations

    list separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     них
    0.31
     őket
    0.29
     нього
    0.29
     honom
    0.28
     niego
    0.28
     nią
    0.27
     ją
    0.27
    ،
    0.27
    ”،
    0.26
     тях
    0.26
    POSITIVE LOGITS
     there
    0.49
     however
    0.44
    there
    0.44
     we
    0.42
     though
    0.40
     especially
    0.39
     albeit
    0.39
     they
    0.35
     it
    0.35
     particularly
    0.34
    Act Density 0.350%

    No Known Activations