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

    Neuronpedia

    INDEX
    Explanations

    New York places

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Syracuse
    0.72
     Ithaca
    0.70
     Buffalo
    0.70
     Rochester
    0.69
    Roche
    0.64
     Utica
    0.62
    Buffalo
    0.62
     Rome
    0.61
     Ole
    0.60
     buffalo
    0.60
    POSITIVE LOGITS
     поза
    0.38
     Wizard
    0.37
    స్తే
    0.37
    笋
    0.37
    atly
    0.36
     добиться
    0.36
     সাম্প্র
    0.36
    пят
    0.36
    爿
    0.36
    Unicode
    0.36
    Act Density 0.007%

    No Known Activations