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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -derived
    -0.08
    谁都
    -0.07
    ጸ
    -0.07
    dealloc
    -0.07
     Xamarin
    -0.07
    쭤
    -0.07
     khả
    -0.07
    뛔
    -0.07
    _Checked
    -0.06
    แถ
    -0.06
    POSITIVE LOGITS
    `s
    0.07
    iquement
    0.07
     Stephens
    0.07
     --
    0.07
    rego
    0.07
    /Desktop
    0.07
    	thread
    0.06
     Juli
    0.06
    >P
    0.06
     Lund
    0.06
    Act Density 0.044%

    No Known Activations