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

    Neuronpedia

    INDEX
    Explanations

    finding a home

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     S
    0.54
     terrible
    0.52
     horrible
    0.51
     I
    0.49
    0.48
     '
    0.48
     moves
    0.47
     settling
    0.47
     mood
    0.46
     Kitchen
    0.46
    POSITIVE LOGITS
    ceti
    0.55
     findPlayer
    0.55
     మొక్క
    0.51
    osx
    0.51
     شاید
    0.50
     couro
    0.50
     outcast
    0.48
     trasmissione
    0.48
    )//
    0.48
    核
    0.48
    Act Density 0.000%

    No Known Activations