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

    Neuronpedia

    INDEX
    Explanations

    cities, manufacturing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Manufacturing
    -0.75
     Wheels
    -0.71
     bus
    -0.68
     hub
    -0.68
     manufacturing
    -0.66
    hub
    -0.65
    Manufacturing
    -0.65
     hubs
    -0.63
    rungsseite
    -0.63
    manufacturing
    -0.62
    POSITIVE LOGITS
     immig
    0.55
     thicken
    0.55
     Immig
    0.53
     doublet
    0.53
     Monfieur
    0.53
     myſelf
    0.52
     Dinah
    0.51
    }])
    0.51
     Agamemnon
    0.51
    Hentet
    0.50
    Act Density 0.096%

    No Known Activations