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

    Neuronpedia

    INDEX
    Explanations

    words starting with car

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    platten
    0.91
    chatroom
    0.87
    ური
    0.85
     Recherches
    0.84
    doo
    0.84
    izabeth
    0.83
    dP
    0.82
    Predictions
    0.82
    sah
    0.82
    ем
    0.82
    POSITIVE LOGITS
    loads
    0.98
    negie
    0.96
    refour
    0.96
    uthers
    0.90
    クター
    0.88
     hidrógeno
    0.87
     chemo
    0.87
    ichael
    0.86
     MediaQuery
    0.85
     loads
    0.84
    Act Density 0.122%

    No Known Activations