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

    Neuronpedia

    INDEX
    Explanations

    idence

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jump
    -0.08
    Jump
    -0.07
    	payload
    -0.07
     BP
    -0.07
     power
    -0.07
     Bağ
    -0.06
     cutting
    -0.06
     filter
    -0.06
     Powerful
    -0.06
     Jump
    -0.06
    POSITIVE LOGITS
     residence
    0.14
     Residence
    0.12
     reside
    0.11
     residences
    0.11
     resident
    0.09
     residing
    0.09
     resides
    0.09
     residents
    0.08
    resident
    0.08
     residency
    0.08
    Act Density 0.014%

    No Known Activations