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

    Neuronpedia

    INDEX
    Explanations

    ali

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Johnson
    -0.07
     voxel
    -0.07
     цю
    -0.07
    lient
    -0.06
     Django
    -0.06
     Hutch
    -0.06
    frica
    -0.06
     magnificent
    -0.06
    Hur
    -0.06
     turno
    -0.06
    POSITIVE LOGITS
     falls
    0.06
     Loop
    0.06
     routines
    0.06
     fluct
    0.06
    饮
    0.06
     hacks
    0.06
     Excellence
    0.06
    .getPort
    0.06
     przed
    0.06
     clumsy
    0.06
    Act Density 0.001%

    No Known Activations