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

    Neuronpedia

    INDEX
    Explanations

    prior to, lingers in

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     For
    0.51
    就很
    0.49
     Water
    0.48
     regexp
    0.48
     Hip
    0.48
    FROM
    0.47
    Water
    0.47
     hipp
    0.47
    َهُ
    0.47
     בה
    0.46
    POSITIVE LOGITS
    ફેદ
    0.50
    φαν
    0.48
    igos
    0.47
    lieben
    0.46
    囦
    0.46
    mány
    0.45
    ಪ್ಪು
    0.45
     alkaloids
    0.45
     Optionen
    0.45
    ktiv
    0.45
    Act Density 0.000%

    No Known Activations