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

    Neuronpedia

    INDEX
    Explanations

    time period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     gm
    -0.06
     subdued
    -0.06
    假
    -0.06
    інь
    -0.06
    oes
    -0.06
    StateManager
    -0.06
    md
    -0.06
                                    
    -0.06
    алося
    -0.06
     دارد
    -0.06
    POSITIVE LOGITS
     pInfo
    0.07
    γχ
    0.06
     апр
    0.06
    SPEC
    0.06
     Paren
    0.06
     věc
    0.06
     дити
    0.06
     typo
    0.06
    �
    0.06
    leck
    0.06
    Act Density 0.150%

    No Known Activations