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

    Neuronpedia

    INDEX
    Explanations

    code and mathematics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Samsung
    -0.06
     consolation
    -0.06
     Reflex
    -0.06
     slowed
    -0.06
     PARTY
    -0.06
    Privacy
    -0.06
    rieve
    -0.06
     pride
    -0.06
    Numbers
    -0.06
     Anne
    -0.06
    POSITIVE LOGITS
     Moscow
    0.07
    FirstName
    0.07
    _HAVE
    0.07
    ym
    0.06
    ğa
    0.06
     ал
    0.06
    牧
    0.06
     tương
    0.06
     CONTRIBUTORS
    0.06
     �
    0.06
    Act Density 0.040%

    No Known Activations