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

    Neuronpedia

    INDEX
    Explanations

    Gem

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hran
    -0.07
    Ap
    -0.07
     Layers
    -0.06
    /rules
    -0.06
    ]])
    -0.06
     Lahore
    -0.06
    -stars
    -0.06
    )frame
    -0.06
    anchise
    -0.06
    $fields
    -0.06
    POSITIVE LOGITS
    .SelectedValue
    0.07
    licate
    0.06
    801
    0.06
     Court
    0.06
     preventing
    0.06
     нерв
    0.06
     Moss
    0.06
    odia
    0.06
     reimb
    0.06
     проти
    0.06
    Act Density 0.000%

    No Known Activations