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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hop
    -0.07
    AJOR
    -0.07
     caves
    -0.06
     Cz
    -0.06
    agan
    -0.06
    -last
    -0.06
    Deep
    -0.06
     containers
    -0.06
    ovky
    -0.06
    BaseContext
    -0.06
    POSITIVE LOGITS
    습
    0.06
     müda
    0.06
    ।
    0.06
     Processes
    0.06
    ,”
    0.06
    ]",
    0.06
    ớp
    0.06
    άλ
    0.06
     skuteč
    0.06
    -pay
    0.06
    Act Density 0.036%

    No Known Activations