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

    Neuronpedia

    INDEX
    Explanations

    ghost

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    rpm
    -0.07
    !”
    -0.07
     совершенно
    -0.07
     VB
    -0.06
     dire
    -0.06
     Covenant
    -0.06
    .ActionEvent
    -0.06
    Comparison
    -0.06
    Timeout
    -0.06
     playground
    -0.06
    POSITIVE LOGITS
     ghosts
    0.07
    στο
    0.07
     enfants
    0.06
     neod
    0.06
     єв
    0.06
    стит
    0.06
     spirits
    0.06
    -backed
    0.06
     WARNING
    0.06
    	ADD
    0.06
    Act Density 0.019%

    No Known Activations