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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     WAN
    -0.07
    	damage
    -0.07
    _PROVID
    -0.06
     Longitude
    -0.06
     Trav
    -0.06
    getResource
    -0.06
    .Receive
    -0.06
    startup
    -0.06
     zemi
    -0.06
    -buy
    -0.06
    POSITIVE LOGITS
    (commit
    0.07
    !!↵↵
    0.06
     subscribed
    0.06
     controversy
    0.06
     його
    0.06
    isu
    0.06
    _SAMPLES
    0.06
     cooperating
    0.06
    ्प
    0.06
     telescope
    0.06
    Act Density 0.004%

    No Known Activations