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

    Neuronpedia

    INDEX
    Explanations

    therapy

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     benchmark
    -0.06
    ","");↵
    -0.06
     fue
    -0.06
     Couple
    -0.06
     �
    -0.06
    _read
    -0.06
    _oid
    -0.06
            
↵        
↵
    -0.06
     Reve
    -0.06
     critique
    -0.06
    POSITIVE LOGITS
     prevented
    0.07
    (settings
    0.07
    ーダ
    0.07
     river
    0.07
     işlemi
    0.06
     котором
    0.06
    -category
    0.06
    ώνα
    0.06
     inhab
    0.06
    -sensitive
    0.06
    Act Density 0.018%

    No Known Activations