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

    Neuronpedia

    INDEX
    Explanations

    URLs, code, and references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Off
    0.56
    getDefaultSh
    0.51
    ifax
    0.51
    Bell
    0.50
    off
    0.50
    Microelectronics
    0.49
    With
    0.49
     Thiel
    0.48
    Do
    0.47
    Di
    0.47
    POSITIVE LOGITS
     perspici
    0.60
     wirtschaft
    0.60
     conveyors
    0.59
    躋
    0.59
     egregious
    0.59
     testimonial
    0.59
     destinat
    0.58
     ekonom
    0.58
    ិន
    0.57
     erricht
    0.57
    Act Density 0.001%

    No Known Activations