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

    Neuronpedia

    INDEX
    Explanations

    costs, speech, Sinatra, update

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rami
    0.40
    ock
    0.40
    RAM
    0.40
     Rams
    0.38
    ችን
    0.38
     Poli
    0.38
    xlim
    0.37
     deepest
    0.36
    spinner
    0.36
     পারছি
    0.36
    POSITIVE LOGITS
     Sturgeon
    0.43
     dilwale
    0.39
     Stahl
    0.39
     bitters
    0.38
     carboxyl
    0.38
    لز
    0.37
     contexte
    0.37
     contesto
    0.37
     ambiente
    0.37
     stills
    0.36
    Act Density 0.000%

    No Known Activations