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

    Neuronpedia

    INDEX
    Explanations

    it

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sun
    -0.07
    尽
    -0.07
    _Service
    -0.07
     rightly
    -0.06
     dint
    -0.06
    oyo
    -0.06
     mush
    -0.06
     CONTROL
    -0.06
    enk
    -0.06
     hunt
    -0.06
    POSITIVE LOGITS
    Deployment
    0.06
    vim
    0.06
    Fin
    0.06
    roller
    0.06
     Vie
    0.06
     سلس
    0.06
     cervical
    0.06
    %)↵
    0.06
    (email
    0.05
     Ethiopian
    0.05
    Act Density 0.000%

    No Known Activations