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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cứ
    -0.07
    she
    -0.06
    adients
    -0.06
    titles
    -0.06
     Relay
    -0.06
    िण
    -0.06
    ircular
    -0.06
    ох
    -0.06
    anke
    -0.06
    may
    -0.06
    POSITIVE LOGITS
     कहन
    0.06
    Disconnect
    0.06
     jackets
    0.06
     SendMessage
    0.06
     tackled
    0.06
    .dw
    0.06
    acct
    0.06
    ctype
    0.06
     grenade
    0.06
     �
    0.06
    Act Density 0.341%

    No Known Activations