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

    Neuronpedia

    INDEX
    Explanations

    DELETE, index, Complement, ID

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ल्प
    0.40
    hof
    0.38
    બર
    0.38
    ்ச
    0.38
    otr
    0.37
     Markle
    0.37
    ers
    0.37
    ǒ
    0.37
    ong
    0.37
    ifferentiate
    0.37
    POSITIVE LOGITS
    Mie
    0.42
     Mie
    0.42
     Tokyo
    0.38
    prescription
    0.37
     тях
    0.37
     sådan
    0.36
    ASES
    0.35
    তখন
    0.35
    صل
    0.35
     یخ
    0.35
    Act Density 0.000%

    No Known Activations