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

    Neuronpedia

    INDEX
    Explanations

    Land

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arella
    -0.07
    isoner
    -0.07
    multip
    -0.07
    ीब
    -0.07
    ーロ
    -0.06
    arta
    -0.06
    BS
    -0.06
     člově
    -0.06
    astle
    -0.06
    aro
    -0.06
    POSITIVE LOGITS
     �
    0.07
     disillusion
    0.07
    (CancellationToken
    0.06
    vatel
    0.06
     jedin
    0.06
     있는데
    0.06
     �
    0.06
    	ret
    0.06
     Schwe
    0.06
     Komm
    0.06
    Act Density 0.182%

    No Known Activations