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

    Neuronpedia

    INDEX
    Explanations

    INSERT INTO column

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     подобных
    0.18
     do
    0.17
     ce
    0.17
     ase
    0.16
     soy
    0.16
     lia
    0.16
     sexually
    0.16
     include
    0.16
     cun
    0.16
     openly
    0.16
    POSITIVE LOGITS
    Flare
    0.17
     Therap
    0.16
    Lambert
    0.15
    RESET
    0.15
    Reconnect
    0.15
    Renewal
    0.15
    Signup
    0.15
    Saver
    0.15
    Rest
    0.14
    AIR
    0.14
    Act Density 0.002%

    No Known Activations