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

    Neuronpedia

    INDEX
    Explanations

    code commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arently
    -0.08
     Cara
    -0.07
    ountain
    -0.07
    824
    -0.07
     DU
    -0.07
     teknik
    -0.06
    stable
    -0.06
     expecting
    -0.06
    >+
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Це
    0.08
    รงเร
    0.07
     Moreover
    0.06
     decorations
    0.06
     ninguna
    0.06
     fim
    0.06
     Gins
    0.06
    óln
    0.06
    nem
    0.06
     Å
    0.06
    Act Density 0.005%

    No Known Activations