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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     가
    -0.07
    くれ
    -0.07
     komen
    -0.06
    /User
    -0.06
     соці
    -0.06
     �
    -0.06
    　j
    -0.06
     ส
    -0.06
    rooms
    -0.06
     기타
    -0.06
    POSITIVE LOGITS
     Voldemort
    0.07
    earable
    0.07
     HD
    0.07
    _modified
    0.06
     PX
    0.06
     Duffy
    0.06
    Expiration
    0.06
    BOOST
    0.06
    _simulation
    0.06
    antage
    0.06
    Act Density 0.008%

    No Known Activations