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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Mu
    -0.07
    محمد
    -0.07
     Solomon
    -0.07
     tedbir
    -0.06
    令人
    -0.06
     перест
    -0.06
    odí
    -0.06
    OWER
    -0.06
    _Task
    -0.06
    ์กร
    -0.06
    POSITIVE LOGITS
    	in
    0.07
     Hp
    0.07
     tin
    0.07
    xAD
    0.07
    (),
    0.07
    /il
    0.07
    InlineData
    0.06
     IN
    0.06
     disclosing
    0.06
    .Virtual
    0.06
    Act Density 0.000%

    No Known Activations