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

    Neuronpedia

    INDEX
    Explanations

    up

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Defaults
    -0.07
     rivers
    -0.06
     terrified
    -0.06
    bitcoin
    -0.06
    culate
    -0.06
     obligations
    -0.06
     attic
    -0.06
     valid
    -0.06
    	G
    -0.06
     angled
    -0.06
    POSITIVE LOGITS
     nắm
    0.07
    ipa
    0.07
     Chef
    0.06
    &S
    0.06
     IPCC
    0.06
     mainstream
    0.06
    업
    0.06
    ?type
    0.06
     bols
    0.06
    때
    0.06
    Act Density 0.016%

    No Known Activations