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

    Neuronpedia

    INDEX
    Explanations

    regret

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tied
    -0.07
    (U
    -0.07
    援
    -0.07
     thinner
    -0.06
    ่ใช
    -0.06
     Sponsor
    -0.06
     stolen
    -0.06
    -ste
    -0.06
    holder
    -0.06
     naam
    -0.06
    POSITIVE LOGITS
     regrets
    0.14
     regret
    0.14
    Register
    0.07
     grate
    0.07
     remorse
    0.07
     szer
    0.07
     Despite
    0.07
    ろ
    0.07
    Thought
    0.07
    ?<
    0.07
    Act Density 0.003%

    No Known Activations