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

    Neuronpedia

    INDEX
    Explanations

    physical dimensions/measurements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    casecmp
    -0.07
     iP
    -0.07
    uve
    -0.06
    GO
    -0.06
     đoạn
    -0.06
    .met
    -0.06
     pornôs
    -0.06
    Postal
    -0.06
    Break
    -0.06
     Pull
    -0.06
    POSITIVE LOGITS
    BadRequest
    0.07
     distributor
    0.07
    			 ↵
    0.06
     Closet
    0.06
     rendre
    0.06
     tempt
    0.06
    		  ↵
    0.06
     potentially
    0.06
     sokak
    0.06
     emotional
    0.06
    Act Density 0.032%

    No Known Activations