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

    Neuronpedia

    INDEX
    Explanations

    statement terminators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resuspended
    0.41
    COU
    0.40
     eigenfunctions
    0.39
    Deux
    0.39
     delicioso
    0.39
     kính
    0.39
     sobbing
    0.38
    RAMM
    0.38
    脹
    0.38
    咄
    0.38
    POSITIVE LOGITS
     He
    0.52
    ((
    0.43
    //
    0.38
    ↵
    0.38
    fare
    0.38
    populate
    0.38
    ;
    0.38
    He
    0.37
     setattr
    0.36
     Setting
    0.36
    Act Density 0.070%

    No Known Activations