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

    Neuronpedia

    INDEX
    Explanations

    punctuation and grammar

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     startup
    -0.08
     стар
    -0.08
    Startup
    -0.07
    reci
    -0.07
    (lambda
    -0.07
     starters
    -0.07
    startup
    -0.07
    Bien
    -0.07
     recurrence
    -0.07
     method
    -0.07
    POSITIVE LOGITS
     endet
    0.11
     termina
    0.10
     concluding
    0.10
     terminating
    0.10
    结束
    0.10
     conclude
    0.10
    終了
    0.10
     끝
    0.10
     শেষে
    0.09
     terminou
    0.09
    Act Density 0.026%

    No Known Activations