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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (rand
    -0.09
    един
    -0.08
     Match
    -0.07
    syscall
    -0.07
    ypo
    -0.07
     Accord
    -0.07
    JOR
    -0.07
     sponsored
    -0.07
    OCI
    -0.07
     SPEED
    -0.07
    POSITIVE LOGITS
     Hicks
    0.08
     принима
    0.08
     freely
    0.07
    ,Object
    0.07
    停放
    0.07
    얐
    0.07
     כתובת
    0.07
    インター�
    0.07
     nfs
    0.07
    ידוע
    0.07
    Act Density 0.010%

    No Known Activations