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

    Neuronpedia

    INDEX
    Explanations

    albums

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beard
    -0.07
    중에
    -0.06
     merit
    -0.06
    _events
    -0.06
    ensing
    -0.06
    hores
    -0.06
     اولیه
    -0.06
     T
    -0.06
     bilgi
    -0.06
    زيد
    -0.06
    POSITIVE LOGITS
     provides
    0.07
     上涨
    0.07
     půj
    0.07
    sap
    0.06
    .shiro
    0.06
    _cuda
    0.06
    _slug
    0.06
    ->[
    0.06
     εκεί
    0.06
     지도
    0.06
    Act Density 0.036%

    No Known Activations