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

    Neuronpedia

    INDEX
    Explanations

    using

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    いう
    -0.06
    dddd
    -0.06
     Zombie
    -0.06
    ceptar
    -0.06
    skými
    -0.06
     свои
    -0.06
    よりも
    -0.06
     erratic
    -0.06
    ोस
    -0.06
     Bye
    -0.05
    POSITIVE LOGITS
    (timer
    0.07
    .go
    0.07
    .Environment
    0.07
     invoice
    0.07
     Tokyo
    0.06
    EE
    0.06
     Hash
    0.06
    .Security
    0.06
    MARY
    0.06
    .Alpha
    0.06
    Act Density 0.000%

    No Known Activations