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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     مشين
    -0.75
     supérieurs
    -0.71
    httphttps
    -0.70
     souhait
    -0.69
    EndContext
    -0.69
     découver
    -0.68
     investissements
    -0.67
     natten
    -0.66
    tvguidetime
    -0.66
     consultato
    -0.66
    POSITIVE LOGITS
    Jîn
    0.57
     referenties
    0.50
     drugs
    0.50
     personnel
    0.49
     live
    0.48
     wages
    0.46
    Pyx
    0.45
     fees
    0.44
    ddots
    0.44
    GroupLayout
    0.44
    Act Density 0.001%

    No Known Activations