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

    Neuronpedia

    INDEX
    Explanations

    disclaimers about advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ज्यादातर
    0.52
    常用的
    0.48
     বেশিরভাগ
    0.47
     meestal
    0.46
     focus
    0.46
     সাধারণত
    0.45
     brauchen
    0.45
     বেশির
    0.44
    0.44
     manageable
    0.44
    POSITIVE LOGITS
     opinions
    0.76
    consult
    0.73
    Consult
    0.73
     consultation
    0.72
    Disclaimer
    0.71
     advice
    0.70
     konsult
    0.70
     Consult
    0.68
     consult
    0.68
     consulted
    0.67
    Act Density 0.066%

    No Known Activations