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

    Neuronpedia

    INDEX
    Explanations

    ^

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �്
    -0.08
     разв
    -0.08
    째
    -0.07
    warm
    -0.07
     עוד
    -0.07
     baby's
    -0.07
     ред
    -0.07
     telefonisch
    -0.07
     tact
    -0.07
    häl
    -0.07
    POSITIVE LOGITS
    (target
    0.08
     efectu
    0.08
     gotten
    0.07
     efetu
    0.07
    GM
    0.07
     MMORPG
    0.07
    Custom
    0.07
     esclare
    0.07
     Custom
    0.07
     feitas
    0.07
    Act Density 0.035%

    No Known Activations