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

    Neuronpedia

    INDEX
    Explanations

    minutes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Carn
    -0.07
    Client
    -0.07
     lobbyist
    -0.06
     जह
    -0.06
     '/'
    -0.06
    Talk
    -0.06
     Вар
    -0.06
    kin
    -0.06
    	REG
    -0.06
    .clips
    -0.06
    POSITIVE LOGITS
     ใน
    0.06
     gemacht
    0.06
     problema
    0.06
     díky
    0.06
    _RECE
    0.06
     channels
    0.06
     choice
    0.06
     THIRD
    0.06
     glowing
    0.06
     maxY
    0.06
    Act Density 0.010%

    No Known Activations