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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bere
    -0.08
     управление
    -0.07
     väl
    -0.07
     Kre
    -0.07
    .Done
    -0.07
     propostas
    -0.07
     மீது
    -0.07
    -enter
    -0.07
     firmy
    -0.07
     Proposal
    -0.07
    POSITIVE LOGITS
    Hot
    0.10
     অন্যতম
    0.09
     dintre
    0.09
     أكبر
    0.08
    hot
    0.08
     pilares
    0.08
     wenigen
    0.08
    _hot
    0.08
     Hot
    0.08
    热门
    0.08
    Act Density 0.045%

    No Known Activations