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

    Neuronpedia

    INDEX
    Explanations

    up and down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্যান্ড
    0.56
     бата
    0.47
     episodios
    0.47
     సినీ
    0.47
     offs
    0.46
     scouting
    0.45
     setValue
    0.44
     scopes
    0.44
     episódio
    0.43
    राज्यपाल
    0.42
    POSITIVE LOGITS
    dsb
    0.39
    ever
    0.38
     समस्त
    0.37
    beam
    0.37
     lavish
    0.37
    olian
    0.37
     Ever
    0.36
     haught
    0.36
    arias
    0.36
    Ger
    0.36
    Act Density 0.001%

    No Known Activations