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

    Neuronpedia

    INDEX
    Explanations

    Los Angeles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    eval
    0.94
    tor
    0.83
    tent
    0.81
    Pe
    0.75
    tio
    0.74
    inplace
    0.74
    tien
    0.74
    ių
    0.74
    deselect
    0.73
    tid
    0.73
    POSITIVE LOGITS
     flaps
    1.04
     angeles
    1.03
     XVI
    0.95
     lax
    0.87
     ends
    0.85
     XIII
    0.85
     wires
    0.85
     eaux
    0.83
     XIV
    0.83
     pasajeros
    0.82
    Act Density 0.030%

    No Known Activations