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

    Neuronpedia

    INDEX
    Explanations

    observation or discovery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :
↵
↵
    -0.07
     guardar
    -0.07
    	query
    -0.07
     BK
    -0.06
     Moore
    -0.06
     Schiff
    -0.06
    ，该
    -0.06
    it
    -0.06
    terní
    -0.06
     Deze
    -0.06
    POSITIVE LOGITS
    _NEW
    0.07
    _RESOURCE
    0.06
    .percent
    0.06
     prio
    0.06
    кта
    0.06
     overwritten
    0.06
    _wallet
    0.06
     concessions
    0.06
    ิดข
    0.06
    glyphicon
    0.06
    Act Density 0.210%

    No Known Activations