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

    Neuronpedia

    INDEX
    Explanations

    skating

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jacket
    -0.07
     passes
    -0.06
     LIFE
    -0.06
     researching
    -0.06
    	field
    -0.06
    แรก
    -0.06
     OF
    -0.06
    _enter
    -0.06
    ине
    -0.06
    SORT
    -0.05
    POSITIVE LOGITS
    _likes
    0.07
    ’am
    0.07
    >y
    0.06
    ;m
    0.06
    .JOptionPane
    0.06
    στρο
    0.06
     kalp
    0.06
    μάτων
    0.06
     scams
    0.06
     投稿
    0.06
    Act Density 0.017%

    No Known Activations