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

    Neuronpedia

    INDEX
    Explanations

    Central Park

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Brain
    0.76
     Engineered
    0.74
    Login
    0.73
     Post
    0.73
     Visa
    0.73
    <unused738>
    0.72
     Firewall
    0.71
     Node
    0.71
     Construction
    0.71
     GMO
    0.70
    POSITIVE LOGITS
     acts
    0.84
    addresses
    0.81
     bords
    0.78
    acts
    0.77
    uya
    0.77
     barking
    0.75
     screams
    0.74
     краси
    0.73
     glimpses
    0.73
     crying
    0.72
    Act Density 0.000%

    No Known Activations