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

    Neuronpedia

    INDEX
    Explanations

    prepositions followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     and
    0.53
    ون
    0.40
    and
    0.39
     specializing
    0.38
     anecdote
    0.37
     For
    0.36
    ある
    0.36
    లో
    0.36
    </td>
    0.36
    на
    0.36
    POSITIVE LOGITS
    }$.
    0.46
    ។
    0.40
    MGMT
    0.40
    odeling
    0.40
    kých
    0.39
    INPUT
    0.38
    LABEL
    0.38
    कांग्रेस
    0.38
    URLs
    0.38
    barplot
    0.38
    Act Density 0.172%

    No Known Activations