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

    Neuronpedia

    INDEX
    Explanations

    roof

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     protector
    -0.07
    _Controller
    -0.07
     unus
    -0.07
    either
    -0.07
     considerations
    -0.07
    .IO
    -0.06
     tijd
    -0.06
    ?q
    -0.06
    =i
    -0.06
     either
    -0.06
    POSITIVE LOGITS
     Cassidy
    0.07
     Melbourne
    0.07
    .BASELINE
    0.06
    phans
    0.06
    -%
    0.06
    _ring
    0.06
     حم
    0.06
    _EV
    0.06
    ANK
    0.06
     بشر
    0.06
    Act Density 0.043%

    No Known Activations