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

    Neuronpedia

    INDEX
    Explanations

    host

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    STOP
    -0.07
     ένα
    -0.06
    _answers
    -0.06
    乐
    -0.06
    SUR
    -0.06
     ל
    -0.06
    .to
    -0.06
    	Command
    -0.06
     Girlfriend
    -0.06
     Clearance
    -0.06
    POSITIVE LOGITS
    .ACT
    0.08
     Highlands
    0.07
     ain
    0.06
    abe
    0.06
    amina
    0.06
     gcc
    0.06
    maids
    0.06
    xdd
    0.06
     thiếu
    0.06
    amine
    0.06
    Act Density 0.000%

    No Known Activations